{
"meta": {
"tool": "ModelCompass",
"powered_by": "Wux AI",
"website": "https://modelcompass.wuxai.com",
"source": "openrouter",
"generated_at": 1782247537,
"generated_iso": "2026-06-23T20:45:37+00:00",
"model_count": 334,
"license_note": "Benchmark- en prijsdata afkomstig van OpenRouter en Artificial Analysis."
},
"tasks": [
{
"id": "writing",
"label": "E-mails & teksten schrijven",
"desc": "Vlotte, correcte en natuurlijke teksten in het Nederlands."
},
{
"id": "summarize",
"label": "Documenten samenvatten",
"desc": "Lange stukken tekst snel en accuraat inkorten."
},
{
"id": "kb-search",
"label": "Kennisbank doorzoeken",
"desc": "Snel het juiste antwoord vinden in je eigen documenten en kennisbank."
},
{
"id": "kb-analyze",
"label": "Kennisbank-data analyseren",
"desc": "Patronen, inzichten en samenhang uit je kennisbank halen."
},
{
"id": "kb-assistant",
"label": "Kennisbank-assistent (chatbot)",
"desc": "Medewerkers of klanten vragen laten stellen aan je kennisbank."
},
{
"id": "translate",
"label": "Vertalen",
"desc": "Betrouwbaar vertalen tussen talen, met behoud van toon."
},
{
"id": "analysis",
"label": "Data & Excel analyseren",
"desc": "Cijfers interpreteren, formules en overzichten maken."
},
{
"id": "coding",
"label": "Programmeren & automatiseren",
"desc": "Code schrijven, scripts bouwen en technische taken."
},
{
"id": "brainstorm",
"label": "Brainstormen & ideeën",
"desc": "Creatieve invalshoeken en frisse ideeën genereren."
},
{
"id": "chat",
"label": "Klantenservice & chat",
"desc": "Snelle, vriendelijke antwoorden tegen lage kosten."
},
{
"id": "research",
"label": "Onderzoek & uitzoeken",
"desc": "Diepgaand redeneren over complexe onderwerpen."
},
{
"id": "agents",
"label": "Zelfstandig taken uitvoeren",
"desc": "Meerstaps-taken die het model zelfstandig afhandelt."
},
{
"id": "vision",
"label": "Afbeeldingen & documenten lezen",
"desc": "Foto’s, scans en schermafbeeldingen begrijpen."
},
{
"id": "image",
"label": "Afbeeldingen maken",
"desc": "Beeld genereren of bewerken op basis van een beschrijving."
}
],
"models": [
{
"id": "anthropic/claude-fable-5",
"slug": "anthropic/claude-5-fable-20260609",
"name": "Claude Fable 5",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...",
"created": 1781007515,
"created_human": "9 jun 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 10,
"completion_per_1m": 50,
"blended_per_1m": 20,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$20 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 59.9,
"coding_index": 76.5,
"math_index": null,
"agentic_index": 52.8,
"mmlu_pro": null,
"gpqa": 92.6,
"hle": 53.3,
"livecodebench": null,
"scicode": 60.2,
"aime": null,
"ifbench": 63.5,
"tau2": 98.5,
"terminalbench": 84.6,
"design_arena": {
"overall_elo": 1371,
"code_elo": 1350,
"count": 11,
"top": [
{
"category": "agentichtmlslides",
"elo": 1254,
"rank": 1
},
{
"category": "agenticslides(html)",
"elo": 1252,
"rank": 1
},
{
"category": "htmlslides",
"elo": 1261,
"rank": 1
},
{
"category": "asciiart",
"elo": 1368,
"rank": 1
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 86,
"coding": 96,
"writing": 86,
"agentic": 96,
"overall": 90
},
"stars": {
"intelligence": 4,
"coding": 5,
"writing": 4,
"agentic": 5,
"speed": 3
},
"popularity": 89,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-fable-5",
"available": false,
"unavailable_reason": "Dit model is momenteel niet beschikbaar.",
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "premium",
"label": "Topkwaliteit, maar prijzig",
"tone": "amber",
"icon": "sparkle",
"desc": "Hoogste kwaliteit, maar je betaalt fors extra voor een kleine verbetering. Alleen kiezen als je écht het beste nodig hebt.",
"score": 14
},
"curated": false,
"pop_rank": null
},
{
"id": "anthropic/claude-opus-4.8-fast",
"slug": "anthropic/claude-4.8-opus-fast-20260528",
"name": "Claude Opus 4.8 (Fast)",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode",
"created": 1779913703,
"created_human": "27 mei 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 10,
"completion_per_1m": 50,
"blended_per_1m": 20,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$20 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 70.4,
"ttft_seconds": 25.33
},
"benchmarks": {
"intelligence_index": 55.7,
"coding_index": 74.3,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 92,
"hle": 45.7,
"livecodebench": null,
"scicode": 53.5,
"aime": null,
"ifbench": 62.2,
"tau2": 94.4,
"terminalbench": 84.6,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 80,
"coding": 93,
"writing": 80,
"agentic": 100,
"overall": 86
},
"stars": {
"intelligence": 4,
"coding": 5,
"writing": 4,
"agentic": 5,
"speed": 3
},
"popularity": 70,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.8-fast",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": true,
"pop_rank": 19
},
{
"id": "anthropic/claude-opus-4.8",
"slug": "anthropic/claude-4.8-opus-20260528",
"name": "Claude Opus 4.8",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Opus 4.8 is Anthropic's highly capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...",
"created": 1779905091,
"created_human": "27 mei 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 25,
"blended_per_1m": 10,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$10 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 70.4,
"ttft_seconds": 25.33
},
"benchmarks": {
"intelligence_index": 55.7,
"coding_index": 74.3,
"math_index": null,
"agentic_index": 47.2,
"mmlu_pro": null,
"gpqa": 92,
"hle": 45.7,
"livecodebench": null,
"scicode": 53.5,
"aime": null,
"ifbench": 62.2,
"tau2": 94.4,
"terminalbench": 84.6,
"design_arena": {
"overall_elo": 1280,
"code_elo": 1282,
"count": 20,
"top": [
{
"category": "androidnative",
"elo": 1346,
"rank": 1
},
{
"category": "mobileapps",
"elo": 1276,
"rank": 1
},
{
"category": "agenticgamedev",
"elo": 1271,
"rank": 2
},
{
"category": "agenticslides",
"elo": 1294,
"rank": 2
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 80,
"coding": 93,
"writing": 80,
"agentic": 86,
"overall": 84
},
"stars": {
"intelligence": 4,
"coding": 5,
"writing": 4,
"agentic": 4,
"speed": 3
},
"popularity": 89,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.8",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": true,
"pop_rank": 1
},
{
"id": "anthropic/claude-opus-4.7-fast",
"slug": "anthropic/claude-4.7-opus-fast-20260512",
"name": "Claude Opus 4.7 (Fast)",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode",
"created": 1778613011,
"created_human": "12 mei 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 30,
"completion_per_1m": 150,
"blended_per_1m": 60,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$60 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 58.3,
"ttft_seconds": 15.64
},
"benchmarks": {
"intelligence_index": 53.5,
"coding_index": 73.6,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 91.4,
"hle": 39.6,
"livecodebench": null,
"scicode": 54.5,
"aime": null,
"ifbench": 58.6,
"tau2": 88.6,
"terminalbench": 83.1,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 76,
"coding": 92,
"writing": 76,
"agentic": 100,
"overall": 83
},
"stars": {
"intelligence": 4,
"coding": 5,
"writing": 4,
"agentic": 5,
"speed": 2
},
"popularity": 67,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.7-fast",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "premium",
"label": "Topkwaliteit, maar prijzig",
"tone": "amber",
"icon": "sparkle",
"desc": "Hoogste kwaliteit, maar je betaalt fors extra voor een kleine verbetering. Alleen kiezen als je écht het beste nodig hebt.",
"score": 8
},
"curated": true,
"pop_rank": 23
},
{
"id": "openai/gpt-5.5",
"slug": "openai/gpt-5.5-20260423",
"name": "GPT-5.5",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...",
"created": 1777051893,
"created_human": "24 apr 2026",
"knowledge_cutoff": "2025-12-01",
"context_length": 1050000,
"context_human": "1.1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 30,
"blended_per_1m": 11.25,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$11 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 58.1,
"ttft_seconds": 15.45
},
"benchmarks": {
"intelligence_index": 54.8,
"coding_index": 74.9,
"math_index": null,
"agentic_index": 44.9,
"mmlu_pro": null,
"gpqa": 93.5,
"hle": 44.3,
"livecodebench": null,
"scicode": 56.1,
"aime": null,
"ifbench": 75.9,
"tau2": 93.9,
"terminalbench": 84.3,
"design_arena": {
"overall_elo": 1299,
"code_elo": 1297,
"count": 21,
"top": [
{
"category": "asciiart",
"elo": 1315,
"rank": 3
},
{
"category": "gamedev",
"elo": 1350,
"rank": 3
},
{
"category": "svg",
"elo": 1286,
"rank": 4
},
{
"category": "agenticgamedev",
"elo": 1211,
"rank": 5
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 78,
"coding": 94,
"writing": 78,
"agentic": 82,
"overall": 82
},
"stars": {
"intelligence": 4,
"coding": 5,
"writing": 4,
"agentic": 4,
"speed": 2
},
"popularity": 86,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.5",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": true,
"pop_rank": 2
},
{
"id": "anthropic/claude-opus-4.7",
"slug": "anthropic/claude-4.7-opus-20260416",
"name": "Claude Opus 4.7",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...",
"created": 1776351100,
"created_human": "16 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 25,
"blended_per_1m": 10,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$10 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 58.3,
"ttft_seconds": 15.64
},
"benchmarks": {
"intelligence_index": 53.5,
"coding_index": 73.6,
"math_index": null,
"agentic_index": 44.4,
"mmlu_pro": null,
"gpqa": 91.4,
"hle": 39.6,
"livecodebench": null,
"scicode": 54.5,
"aime": null,
"ifbench": 58.6,
"tau2": 88.6,
"terminalbench": 83.1,
"design_arena": {
"overall_elo": 1326,
"code_elo": 1337,
"count": 21,
"top": [
{
"category": "agenticgamedev",
"elo": 1289,
"rank": 1
},
{
"category": "agenticslides",
"elo": 1334,
"rank": 1
},
{
"category": "agenticslides(python-pptx)",
"elo": 1335,
"rank": 1
},
{
"category": "fullstack",
"elo": 1503,
"rank": 1
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 76,
"coding": 92,
"writing": 76,
"agentic": 81,
"overall": 80
},
"stars": {
"intelligence": 4,
"coding": 5,
"writing": 4,
"agentic": 4,
"speed": 2
},
"popularity": 84,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.7",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": true,
"pop_rank": 4
},
{
"id": "openai/gpt-5.4",
"slug": "openai/gpt-5.4-20260305",
"name": "GPT-5.4",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.4 is OpenAI’s frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...",
"created": 1772734352,
"created_human": "5 mrt 2026",
"knowledge_cutoff": null,
"context_length": 1050000,
"context_human": "1.1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2.5,
"completion_per_1m": 15,
"blended_per_1m": 5.625,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$5.6 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 162.6,
"ttft_seconds": 99.76
},
"benchmarks": {
"intelligence_index": 51.4,
"coding_index": 71.1,
"math_index": null,
"agentic_index": 41.1,
"mmlu_pro": null,
"gpqa": 92,
"hle": 41.6,
"livecodebench": null,
"scicode": 56.6,
"aime": null,
"ifbench": 73.9,
"tau2": 87.1,
"terminalbench": 78.3,
"design_arena": {
"overall_elo": 1261,
"code_elo": 1266,
"count": 13,
"top": [
{
"category": "asciiart",
"elo": 1240,
"rank": 11
},
{
"category": "svg",
"elo": 1253,
"rank": 11
},
{
"category": "gamedev",
"elo": 1305,
"rank": 14
},
{
"category": "uicomponent",
"elo": 1300,
"rank": 14
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 73,
"coding": 89,
"writing": 73,
"agentic": 75,
"overall": 77
},
"stars": {
"intelligence": 4,
"coding": 4,
"writing": 4,
"agentic": 4,
"speed": 4
},
"popularity": 78,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.4",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 20
},
"curated": true,
"pop_rank": 7
},
{
"id": "google/gemini-3.5-flash",
"slug": "google/gemini-3.5-flash-20260519",
"name": "Gemini 3.5 Flash",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...",
"created": 1779193800,
"created_human": "19 mei 2026",
"knowledge_cutoff": "2025-01-01",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.5,
"completion_per_1m": 9,
"blended_per_1m": 3.375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 240.8,
"ttft_seconds": 14.02
},
"benchmarks": {
"intelligence_index": 50.2,
"coding_index": 70.1,
"math_index": null,
"agentic_index": 37.4,
"mmlu_pro": null,
"gpqa": 92.2,
"hle": 41,
"livecodebench": null,
"scicode": 53.1,
"aime": null,
"ifbench": 76.3,
"tau2": 95.3,
"terminalbench": 78.7,
"design_arena": {
"overall_elo": 1305,
"code_elo": 1303,
"count": 20,
"top": [
{
"category": "mobileapps",
"elo": 1264,
"rank": 2
},
{
"category": "asciiart",
"elo": 1316,
"rank": 2
},
{
"category": "agenticgamedev",
"elo": 1217,
"rank": 3
},
{
"category": "agenticslides(python-pptx)",
"elo": 1242,
"rank": 3
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 72,
"coding": 88,
"writing": 72,
"agentic": 68,
"overall": 75
},
"stars": {
"intelligence": 4,
"coding": 4,
"writing": 4,
"agentic": 3,
"speed": 5
},
"popularity": 85,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3.5-flash",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": true,
"pop_rank": 3
},
{
"id": "z-ai/glm-5.2",
"slug": "z-ai/glm-5.2-20260616",
"name": "GLM 5.2",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...",
"created": 1781631930,
"created_human": "16 jun 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.98,
"completion_per_1m": 3.08,
"blended_per_1m": 1.505,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.5 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 109.4,
"ttft_seconds": 0.91
},
"benchmarks": {
"intelligence_index": 51.1,
"coding_index": 50.7,
"math_index": null,
"agentic_index": 43.1,
"mmlu_pro": null,
"gpqa": 89.5,
"hle": 40.1,
"livecodebench": null,
"scicode": 50.5,
"aime": null,
"ifbench": 73.3,
"tau2": 99.1,
"terminalbench": 77.9,
"design_arena": {
"overall_elo": 1358,
"code_elo": 1361,
"count": 11,
"top": [
{
"category": "3d",
"elo": 1381,
"rank": 1
},
{
"category": "codecategories",
"elo": 1361,
"rank": 1
},
{
"category": "website",
"elo": 1356,
"rank": 1
},
{
"category": "gamedev",
"elo": 1369,
"rank": 2
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 73,
"coding": 63,
"writing": 73,
"agentic": 78,
"overall": 72
},
"stars": {
"intelligence": 4,
"coding": 3,
"writing": 4,
"agentic": 4,
"speed": 3
},
"popularity": 84,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten"
],
"categories": [
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-5.2",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 35
},
"curated": true,
"pop_rank": 5
},
{
"id": "qwen/qwen3.7-max",
"slug": "qwen/qwen3.7-max-20260520",
"name": "Qwen3.7 Max",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...",
"created": 1779376861,
"created_human": "21 mei 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 3.75,
"blended_per_1m": 1.875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.9 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 200.2,
"ttft_seconds": 1.62
},
"benchmarks": {
"intelligence_index": 46,
"coding_index": 66,
"math_index": null,
"agentic_index": 30.6,
"mmlu_pro": null,
"gpqa": 92.3,
"hle": 38.1,
"livecodebench": null,
"scicode": 48.8,
"aime": null,
"ifbench": 80.5,
"tau2": 94.7,
"terminalbench": 74.5,
"design_arena": {
"overall_elo": 1301,
"code_elo": 1311,
"count": 12,
"top": [
{
"category": "uicomponent",
"elo": 1327,
"rank": 6
},
{
"category": "webapps",
"elo": 1258,
"rank": 7
},
{
"category": "svg",
"elo": 1276,
"rank": 8
},
{
"category": "asciiart",
"elo": 1260,
"rank": 9
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 66,
"coding": 83,
"writing": 66,
"agentic": 56,
"overall": 68
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 5
},
"popularity": 80,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Chat & klantenservice",
"Lange documenten"
],
"categories": [
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.7-max",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": true,
"pop_rank": 6
},
{
"id": "anthropic/claude-opus-4.6",
"slug": "anthropic/claude-4.6-opus-20260205",
"name": "Claude Opus 4.6",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...",
"created": 1770219050,
"created_human": "4 feb 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 25,
"blended_per_1m": 10,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$10 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 60.7,
"ttft_seconds": 1.7
},
"benchmarks": {
"intelligence_index": 37.8,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 84,
"hle": 18.6,
"livecodebench": null,
"scicode": 45.7,
"aime": null,
"ifbench": 44.6,
"tau2": 84.8,
"terminalbench": 48.5,
"design_arena": {
"overall_elo": 1329,
"code_elo": 1342,
"count": 12,
"top": [
{
"category": "mobileapps",
"elo": 1261,
"rank": 3
},
{
"category": "codecategories",
"elo": 1342,
"rank": 3
},
{
"category": "website",
"elo": 1338,
"rank": 3
},
{
"category": "fullstack",
"elo": 1289,
"rank": 4
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 83,
"writing": 54,
"agentic": 100,
"overall": 67
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 67,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.6",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 12
},
"curated": true,
"pop_rank": 24
},
{
"id": "anthropic/claude-opus-4.5",
"slug": "anthropic/claude-4.5-opus-20251124",
"name": "Claude Opus 4.5",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world cod…",
"created": 1764010580,
"created_human": "24 nov 2025",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 25,
"blended_per_1m": 10,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$10 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 76.8,
"ttft_seconds": 12.57
},
"benchmarks": {
"intelligence_index": 40.8,
"coding_index": null,
"math_index": 91.3,
"agentic_index": null,
"mmlu_pro": 89.5,
"gpqa": 86.6,
"hle": 28.4,
"livecodebench": 87.1,
"scicode": 49.5,
"aime": 91.3,
"ifbench": 58,
"tau2": 89.5,
"terminalbench": 47,
"design_arena": {
"overall_elo": 1277,
"code_elo": 1292,
"count": 12,
"top": [
{
"category": "mobileapps",
"elo": 1240,
"rank": 6
},
{
"category": "fullstack",
"elo": 1225,
"rank": 8
},
{
"category": "webapps",
"elo": 1222,
"rank": 11
},
{
"category": "androidnative",
"elo": 1187,
"rank": 12
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 58,
"coding": 69,
"writing": 58,
"agentic": 100,
"overall": 67
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 66,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.5",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": true,
"pop_rank": 28
},
{
"id": "deepseek/deepseek-v4-pro",
"slug": "deepseek/deepseek-v4-pro-20260423",
"name": "DeepSeek V4 Pro",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...",
"created": 1777000679,
"created_human": "24 apr 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.435,
"completion_per_1m": 0.87,
"blended_per_1m": 0.5438,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.54 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 103.6,
"ttft_seconds": 1.08
},
"benchmarks": {
"intelligence_index": 44.3,
"coding_index": 59.4,
"math_index": null,
"agentic_index": 36.4,
"mmlu_pro": null,
"gpqa": 88.8,
"hle": 35.9,
"livecodebench": null,
"scicode": 50,
"aime": null,
"ifbench": 76.5,
"tau2": 96.2,
"terminalbench": 64,
"design_arena": {
"overall_elo": 1261,
"code_elo": 1291,
"count": 11,
"top": [
{
"category": "3d",
"elo": 1333,
"rank": 7
},
{
"category": "gamedev",
"elo": 1305,
"rank": 13
},
{
"category": "codecategories",
"elo": 1291,
"rank": 18
},
{
"category": "godotgamedev",
"elo": 1097,
"rank": 20
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 63,
"coding": 74,
"writing": 63,
"agentic": 66,
"overall": 66
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 3
},
"popularity": 76,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten"
],
"categories": [
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-v4-pro",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 45
},
"curated": true,
"pop_rank": 10
},
{
"id": "z-ai/glm-5-turbo",
"slug": "z-ai/glm-5-turbo-20260315",
"name": "GLM 5 Turbo",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...",
"created": 1773583573,
"created_human": "15 mrt 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.2,
"completion_per_1m": 4,
"blended_per_1m": 1.9,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.9 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 38.1,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 84.7,
"hle": 25.4,
"livecodebench": null,
"scicode": 43.6,
"aime": null,
"ifbench": 73.2,
"tau2": 98.5,
"terminalbench": 33.3,
"design_arena": {
"overall_elo": 1299,
"code_elo": 1322,
"count": 8,
"top": [
{
"category": "3d",
"elo": 1335,
"rank": 6
},
{
"category": "dataviz",
"elo": 1306,
"rank": 7
},
{
"category": "website",
"elo": 1318,
"rank": 7
},
{
"category": "codecategories",
"elo": 1322,
"rank": 8
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 78,
"writing": 54,
"agentic": 100,
"overall": 66
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 5,
"speed": 5
},
"popularity": 66,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Chat & klantenservice"
],
"categories": [
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-5-turbo",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 23
},
"curated": true,
"pop_rank": 29
},
{
"id": "google/gemini-3.1-pro-preview",
"slug": "google/gemini-3.1-pro-preview-20260219",
"name": "Gemini 3.1 Pro Preview",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundati…",
"created": 1771509627,
"created_human": "19 feb 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 12,
"blended_per_1m": 4.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.5 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 139.7,
"ttft_seconds": 27.34
},
"benchmarks": {
"intelligence_index": 46.5,
"coding_index": 68.8,
"math_index": null,
"agentic_index": 21.4,
"mmlu_pro": null,
"gpqa": 94.1,
"hle": 44.7,
"livecodebench": null,
"scicode": 58.9,
"aime": null,
"ifbench": 77.1,
"tau2": 95.6,
"terminalbench": 73.8,
"design_arena": {
"overall_elo": 1300,
"code_elo": 1291,
"count": 21,
"top": [
{
"category": "svg",
"elo": 1344,
"rank": 2
},
{
"category": "asciiart",
"elo": 1312,
"rank": 4
},
{
"category": "agentichtmlslides",
"elo": 1226,
"rank": 5
},
{
"category": "agenticslides(html)",
"elo": 1219,
"rank": 5
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 66,
"coding": 86,
"writing": 66,
"agentic": 39,
"overall": 66
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 2,
"speed": 4
},
"popularity": 76,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3.1-pro-preview",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 20
},
"curated": true,
"pop_rank": 11
},
{
"id": "minimax/minimax-m3",
"slug": "minimax/minimax-m3-20260531",
"name": "MiniMax M3",
"vendor": "MiniMax",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...",
"created": 1780245374,
"created_human": "31 mei 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 1.2,
"blended_per_1m": 0.525,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.53 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 58.7,
"ttft_seconds": 2
},
"benchmarks": {
"intelligence_index": 44.4,
"coding_index": 58.6,
"math_index": null,
"agentic_index": 35.4,
"mmlu_pro": null,
"gpqa": 92.9,
"hle": 37.1,
"livecodebench": null,
"scicode": 45.4,
"aime": null,
"ifbench": 82.9,
"tau2": 88.9,
"terminalbench": 65.2,
"design_arena": {
"overall_elo": 1287,
"code_elo": 1308,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1240,
"rank": 12
},
{
"category": "codecategories",
"elo": 1308,
"rank": 12
},
{
"category": "dataviz",
"elo": 1286,
"rank": 12
},
{
"category": "svg",
"elo": 1250,
"rank": 12
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 63,
"coding": 73,
"writing": 63,
"agentic": 64,
"overall": 65
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 2
},
"popularity": 76,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/minimax/minimax-m3",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 46
},
"curated": true,
"pop_rank": 12
},
{
"id": "z-ai/glm-5",
"slug": "z-ai/glm-5-20260211",
"name": "GLM 5",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivalin…",
"created": 1770829182,
"created_human": "11 feb 2026",
"knowledge_cutoff": null,
"context_length": 202752,
"context_human": "203K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.6,
"completion_per_1m": 1.92,
"blended_per_1m": 0.93,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.93 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 71.4,
"ttft_seconds": 1.05
},
"benchmarks": {
"intelligence_index": 39.5,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 82,
"hle": 27.2,
"livecodebench": null,
"scicode": 46.2,
"aime": null,
"ifbench": 72.3,
"tau2": 98.2,
"terminalbench": 43.2,
"design_arena": {
"overall_elo": 1271,
"code_elo": 1296,
"count": 12,
"top": [
{
"category": "godotgamedev",
"elo": 1237,
"rank": 3
},
{
"category": "androidnative",
"elo": 1236,
"rank": 7
},
{
"category": "mobileapps",
"elo": 1222,
"rank": 11
},
{
"category": "fullstack",
"elo": 1191,
"rank": 13
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 56,
"coding": 70,
"writing": 56,
"agentic": 100,
"overall": 65
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 68,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Zelfstandige taken"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-5",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 32
},
"curated": true,
"pop_rank": 21
},
{
"id": "openai/gpt-5.3-codex",
"slug": "openai/gpt-5.3-codex-20260224",
"name": "GPT-5.3-Codex",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.3-Codex is OpenAI’s advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art…",
"created": 1771959164,
"created_human": "24 feb 2026",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.75,
"completion_per_1m": 14,
"blended_per_1m": 4.8125,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.8 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 101,
"ttft_seconds": 57.95
},
"benchmarks": {
"intelligence_index": 44.3,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 91.5,
"hle": 39.9,
"livecodebench": null,
"scicode": 53.2,
"aime": null,
"ifbench": 75.4,
"tau2": 86,
"terminalbench": 53,
"design_arena": {
"overall_elo": 1187,
"code_elo": 1195,
"count": 13,
"top": [
{
"category": "godotgamedev",
"elo": 1161,
"rank": 15
},
{
"category": "androidnative",
"elo": 1084,
"rank": 20
},
{
"category": "webapps",
"elo": 1118,
"rank": 23
},
{
"category": "asciiart",
"elo": 1196,
"rank": 24
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 63,
"coding": 41,
"writing": 63,
"agentic": 100,
"overall": 64
},
"stars": {
"intelligence": 3,
"coding": 2,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 73,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.3-codex",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": true,
"pop_rank": 15
},
{
"id": "moonshotai/kimi-k2.5",
"slug": "moonshotai/kimi-k2.5-0127",
"name": "Kimi K2.5",
"vendor": "Moonshot AI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...",
"created": 1769487076,
"created_human": "27 jan 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.375,
"completion_per_1m": 2.025,
"blended_per_1m": 0.7875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.79 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 42.6,
"ttft_seconds": 1.25
},
"benchmarks": {
"intelligence_index": 38.1,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 87.9,
"hle": 29.4,
"livecodebench": null,
"scicode": 49,
"aime": null,
"ifbench": 70.2,
"tau2": 95.9,
"terminalbench": 34.8,
"design_arena": {
"overall_elo": 1266,
"code_elo": 1287,
"count": 13,
"top": [
{
"category": "godotgamedev",
"elo": 1256,
"rank": 2
},
{
"category": "fullstack",
"elo": 1183,
"rank": 14
},
{
"category": "webapps",
"elo": 1194,
"rank": 15
},
{
"category": "androidnative",
"elo": 1129,
"rank": 16
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 68,
"writing": 54,
"agentic": 100,
"overall": 64
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 5,
"speed": 2
},
"popularity": 67,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/moonshotai/kimi-k2.5",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 33
},
"curated": true,
"pop_rank": 25
},
{
"id": "openai/gpt-5.2",
"slug": "openai/gpt-5.2-20251211",
"name": "GPT-5.2",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.2 is the frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...",
"created": 1765389775,
"created_human": "10 dec 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.75,
"completion_per_1m": 14,
"blended_per_1m": 4.8125,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.8 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 86.8,
"ttft_seconds": 77.21
},
"benchmarks": {
"intelligence_index": 42.2,
"coding_index": null,
"math_index": 99,
"agentic_index": null,
"mmlu_pro": 87.4,
"gpqa": 90.3,
"hle": 35.4,
"livecodebench": 88.9,
"scicode": 52.1,
"aime": 99,
"ifbench": 75.4,
"tau2": 84.8,
"terminalbench": 47,
"design_arena": {
"overall_elo": 1220,
"code_elo": 1220,
"count": 13,
"top": [
{
"category": "godotgamedev",
"elo": 1183,
"rank": 13
},
{
"category": "webapps",
"elo": 1157,
"rank": 19
},
{
"category": "androidnative",
"elo": 1069,
"rank": 21
},
{
"category": "fullstack",
"elo": 1111,
"rank": 21
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 60,
"coding": 49,
"writing": 60,
"agentic": 100,
"overall": 64
},
"stars": {
"intelligence": 3,
"coding": 2,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 67,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.2",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": true,
"pop_rank": 26
},
{
"id": "moonshotai/kimi-k2.7-code",
"slug": "moonshotai/kimi-k2.7-code-20260612",
"name": "Kimi K2.7 Code",
"vendor": "Moonshot AI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...",
"created": 1781266361,
"created_human": "12 jun 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.74,
"completion_per_1m": 3.5,
"blended_per_1m": 1.43,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.4 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 51.6,
"ttft_seconds": 1.17
},
"benchmarks": {
"intelligence_index": 41.9,
"coding_index": 60.8,
"math_index": null,
"agentic_index": 29.6,
"mmlu_pro": null,
"gpqa": 89.6,
"hle": 32.8,
"livecodebench": null,
"scicode": 47.5,
"aime": null,
"ifbench": 63.1,
"tau2": 90.1,
"terminalbench": 67.4,
"design_arena": {
"overall_elo": 1301,
"code_elo": 1310,
"count": 10,
"top": [
{
"category": "htmlslides",
"elo": 1196,
"rank": 7
},
{
"category": "webapps",
"elo": 1248,
"rank": 8
},
{
"category": "website",
"elo": 1317,
"rank": 9
},
{
"category": "fullstack",
"elo": 1223,
"rank": 10
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 60,
"coding": 76,
"writing": 60,
"agentic": 54,
"overall": 62
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 2
},
"popularity": 77,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/moonshotai/kimi-k2.7-code",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": true,
"pop_rank": 9
},
{
"id": "xiaomi/mimo-v2.5-pro",
"slug": "xiaomi/mimo-v2.5-pro-20260422",
"name": "MiMo-V2.5-Pro",
"vendor": "Xiaomi",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....",
"created": 1776874273,
"created_human": "22 apr 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.435,
"completion_per_1m": 0.87,
"blended_per_1m": 0.5438,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.54 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 50.4,
"ttft_seconds": 2.01
},
"benchmarks": {
"intelligence_index": 42.2,
"coding_index": 60.2,
"math_index": null,
"agentic_index": 29.1,
"mmlu_pro": null,
"gpqa": 86.6,
"hle": 33.8,
"livecodebench": null,
"scicode": 50.2,
"aime": null,
"ifbench": 79.9,
"tau2": 94.2,
"terminalbench": 65.2,
"design_arena": {
"overall_elo": 1299,
"code_elo": 1321,
"count": 7,
"top": [
{
"category": "gamedev",
"elo": 1338,
"rank": 7
},
{
"category": "3d",
"elo": 1327,
"rank": 8
},
{
"category": "codecategories",
"elo": 1321,
"rank": 9
},
{
"category": "dataviz",
"elo": 1298,
"rank": 10
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 60,
"coding": 75,
"writing": 60,
"agentic": 53,
"overall": 62
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 2
},
"popularity": 71,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Lange documenten"
],
"categories": [
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/xiaomi/mimo-v2.5-pro",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 43
},
"curated": true,
"pop_rank": 16
},
{
"id": "moonshotai/kimi-k2.6",
"slug": "moonshotai/kimi-k2.6-20260420",
"name": "Kimi K2.6",
"vendor": "Moonshot AI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...",
"created": 1776699402,
"created_human": "20 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.66,
"completion_per_1m": 3.41,
"blended_per_1m": 1.3475,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.3 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 46.9,
"ttft_seconds": 1.36
},
"benchmarks": {
"intelligence_index": 42.8,
"coding_index": 56,
"math_index": null,
"agentic_index": 30.3,
"mmlu_pro": null,
"gpqa": 91.1,
"hle": 35.9,
"livecodebench": null,
"scicode": 53.5,
"aime": null,
"ifbench": 76,
"tau2": 95.9,
"terminalbench": 57.3,
"design_arena": {
"overall_elo": 1311,
"code_elo": 1328,
"count": 20,
"top": [
{
"category": "agentichtmlslides",
"elo": 1248,
"rank": 2
},
{
"category": "agenticslides(html)",
"elo": 1252,
"rank": 2
},
{
"category": "htmlslides",
"elo": 1252,
"rank": 2
},
{
"category": "3d",
"elo": 1358,
"rank": 3
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 61,
"coding": 70,
"writing": 61,
"agentic": 55,
"overall": 62
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 2
},
"popularity": 78,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/moonshotai/kimi-k2.6",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 30
},
"curated": true,
"pop_rank": 8
},
{
"id": "openai/gpt-5.1",
"slug": "openai/gpt-5.1-20251113",
"name": "GPT-5.1",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.1 is the frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...",
"created": 1763060305,
"created_human": "13 nov 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 104.9,
"ttft_seconds": 30.63
},
"benchmarks": {
"intelligence_index": 38.9,
"coding_index": null,
"math_index": 94,
"agentic_index": null,
"mmlu_pro": 87,
"gpqa": 87.3,
"hle": 26.5,
"livecodebench": 86.8,
"scicode": 43.3,
"aime": 94,
"ifbench": 72.9,
"tau2": 81.9,
"terminalbench": 45.5,
"design_arena": {
"overall_elo": 1209,
"code_elo": 1221,
"count": 9,
"top": [
{
"category": "svg",
"elo": 1205,
"rank": 25
},
{
"category": "mobileapps",
"elo": 1127,
"rank": 29
},
{
"category": "dataviz",
"elo": 1247,
"rank": 29
},
{
"category": "gamedev",
"elo": 1246,
"rank": 33
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 56,
"coding": 49,
"writing": 56,
"agentic": 98,
"overall": 61
},
"stars": {
"intelligence": 3,
"coding": 2,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 62,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.1",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": true,
"pop_rank": 32
},
{
"id": "deepseek/deepseek-v4-flash",
"slug": "deepseek/deepseek-v4-flash-20260423",
"name": "DeepSeek V4 Flash",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...",
"created": 1777000666,
"created_human": "24 apr 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.09,
"completion_per_1m": 0.18,
"blended_per_1m": 0.1125,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.11 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 117.7,
"ttft_seconds": 1.06
},
"benchmarks": {
"intelligence_index": 40.3,
"coding_index": 56.2,
"math_index": null,
"agentic_index": 31.1,
"mmlu_pro": null,
"gpqa": 89.4,
"hle": 32.1,
"livecodebench": null,
"scicode": 44.9,
"aime": null,
"ifbench": 79.2,
"tau2": 95,
"terminalbench": 61.8,
"design_arena": {
"overall_elo": 1229,
"code_elo": 1259,
"count": 8,
"top": [
{
"category": "svg",
"elo": 1211,
"rank": 20
},
{
"category": "3d",
"elo": 1273,
"rank": 24
},
{
"category": "gamedev",
"elo": 1269,
"rank": 26
},
{
"category": "codecategories",
"elo": 1259,
"rank": 29
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 58,
"coding": 70,
"writing": 58,
"agentic": 57,
"overall": 60
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 4
},
"popularity": 71,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-v4-flash",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 78
},
"curated": true,
"pop_rank": 17
},
{
"id": "z-ai/glm-5v-turbo",
"slug": "z-ai/glm-5v-turbo-20260401",
"name": "GLM 5V Turbo",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...",
"created": 1775061458,
"created_human": "1 apr 2026",
"knowledge_cutoff": null,
"context_length": 202752,
"context_human": "203K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.2,
"completion_per_1m": 4,
"blended_per_1m": 1.9,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.9 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 34.5,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 80.9,
"hle": 15.8,
"livecodebench": null,
"scicode": 43.5,
"aime": null,
"ifbench": 61.1,
"tau2": 98.5,
"terminalbench": 32.6,
"design_arena": {
"overall_elo": 1248,
"code_elo": 1279,
"count": 21,
"top": [
{
"category": "androidnative",
"elo": 1267,
"rank": 4
},
{
"category": "godotgamedev",
"elo": 1221,
"rank": 5
},
{
"category": "agenticslides",
"elo": 1171,
"rank": 6
},
{
"category": "agenticslides(python-pptx)",
"elo": 1183,
"rank": 6
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 49,
"coding": 65,
"writing": 49,
"agentic": 100,
"overall": 60
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 5,
"speed": 5
},
"popularity": 71,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-5v-turbo",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 21
},
"curated": true,
"pop_rank": 18
},
{
"id": "anthropic/claude-sonnet-4.6",
"slug": "anthropic/claude-4.6-sonnet-20260217",
"name": "Claude Sonnet 4.6",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Sonnet 4.6 is Anthropic's highly capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...",
"created": 1771342990,
"created_human": "17 feb 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 3,
"completion_per_1m": 15,
"blended_per_1m": 6,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$6.0 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 59.5,
"ttft_seconds": 0.99
},
"benchmarks": {
"intelligence_index": 35.9,
"coding_index": 63,
"math_index": null,
"agentic_index": 40.8,
"mmlu_pro": null,
"gpqa": 79.9,
"hle": 13.2,
"livecodebench": null,
"scicode": 46.9,
"aime": null,
"ifbench": 41.2,
"tau2": 79.5,
"terminalbench": 46.2,
"design_arena": {
"overall_elo": 1307,
"code_elo": 1326,
"count": 14,
"top": [
{
"category": "godotgamedev",
"elo": 1277,
"rank": 1
},
{
"category": "mobileapps",
"elo": 1257,
"rank": 4
},
{
"category": "fullstack",
"elo": 1275,
"rank": 5
},
{
"category": "website",
"elo": 1328,
"rank": 5
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 51,
"coding": 79,
"writing": 51,
"agentic": 74,
"overall": 60
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 4,
"speed": 2
},
"popularity": 68,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 14
},
"curated": true,
"pop_rank": 22
},
{
"id": "google/gemini-3-flash-preview",
"slug": "google/gemini-3-flash-preview-20251217",
"name": "Gemini 3 Flash Preview",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...",
"created": 1765987078,
"created_human": "17 dec 2025",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.5,
"completion_per_1m": 3,
"blended_per_1m": 1.125,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.1 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 230,
"ttft_seconds": 5.78
},
"benchmarks": {
"intelligence_index": 37.8,
"coding_index": null,
"math_index": 97,
"agentic_index": null,
"mmlu_pro": 89,
"gpqa": 89.8,
"hle": 34.7,
"livecodebench": 90.8,
"scicode": 50.6,
"aime": 97,
"ifbench": 78,
"tau2": 80.4,
"terminalbench": 38.6,
"design_arena": {
"overall_elo": 1244,
"code_elo": 1240,
"count": 11,
"top": [
{
"category": "godotgamedev",
"elo": 1219,
"rank": 7
},
{
"category": "agenticslides",
"elo": 1073,
"rank": 9
},
{
"category": "agenticslides(python-pptx)",
"elo": 1075,
"rank": 9
},
{
"category": "fullstack",
"elo": 1131,
"rank": 17
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 54,
"writing": 54,
"agentic": 92,
"overall": 60
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 5,
"speed": 5
},
"popularity": 63,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3-flash-preview",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": true,
"pop_rank": 31
},
{
"id": "z-ai/glm-5.1",
"slug": "z-ai/glm-5.1-20260406",
"name": "GLM 5.1",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...",
"created": 1775578025,
"created_human": "7 apr 2026",
"knowledge_cutoff": null,
"context_length": 202752,
"context_human": "203K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.98,
"completion_per_1m": 3.08,
"blended_per_1m": 1.505,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.5 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 97.5,
"ttft_seconds": 0.79
},
"benchmarks": {
"intelligence_index": 40.2,
"coding_index": 55.8,
"math_index": null,
"agentic_index": 29.9,
"mmlu_pro": null,
"gpqa": 86.8,
"hle": 28,
"livecodebench": null,
"scicode": 43.8,
"aime": null,
"ifbench": 76.3,
"tau2": 97.7,
"terminalbench": 61.8,
"design_arena": {
"overall_elo": 1332,
"code_elo": 1333,
"count": 20,
"top": [
{
"category": "dataviz",
"elo": 1366,
"rank": 2
},
{
"category": "agenticslides",
"elo": 1245,
"rank": 3
},
{
"category": "python-pptxslides",
"elo": 1258,
"rank": 3
},
{
"category": "agenticgamedev",
"elo": 1216,
"rank": 4
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 57,
"coding": 70,
"writing": 57,
"agentic": 54,
"overall": 59
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 3
},
"popularity": 75,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Zelfstandige taken"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-5.1",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 27
},
"curated": true,
"pop_rank": 13
},
{
"id": "openai/gpt-5.4-mini",
"slug": "openai/gpt-5.4-mini-20260317",
"name": "GPT-5.4 Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...",
"created": 1773748178,
"created_human": "17 mrt 2026",
"knowledge_cutoff": "2025-08-31",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.75,
"completion_per_1m": 4.5,
"blended_per_1m": 1.6875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.7 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 192.1,
"ttft_seconds": 4.21
},
"benchmarks": {
"intelligence_index": 40,
"coding_index": 56.1,
"math_index": null,
"agentic_index": 30.2,
"mmlu_pro": null,
"gpqa": 87.5,
"hle": 26.6,
"livecodebench": null,
"scicode": 49.9,
"aime": null,
"ifbench": 73.3,
"tau2": 83.3,
"terminalbench": 59.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 57,
"coding": 70,
"writing": 57,
"agentic": 55,
"overall": 59
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 4
},
"popularity": 54,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.4-mini",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 26
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.6-plus",
"slug": "qwen/qwen3.6-plus-04-02",
"name": "Qwen3.6 Plus",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...",
"created": 1775133557,
"created_human": "2 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.325,
"completion_per_1m": 1.95,
"blended_per_1m": 0.7313,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.73 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 52.6,
"ttft_seconds": 1.53
},
"benchmarks": {
"intelligence_index": 39.6,
"coding_index": 54.5,
"math_index": null,
"agentic_index": 27.6,
"mmlu_pro": null,
"gpqa": 88.2,
"hle": 25.7,
"livecodebench": null,
"scicode": 40.7,
"aime": null,
"ifbench": 75.2,
"tau2": 97.7,
"terminalbench": 61.4,
"design_arena": {
"overall_elo": 1253,
"code_elo": 1275,
"count": 8,
"top": [
{
"category": "svg",
"elo": 1217,
"rank": 19
},
{
"category": "uicomponent",
"elo": 1284,
"rank": 21
},
{
"category": "3d",
"elo": 1276,
"rank": 23
},
{
"category": "codecategories",
"elo": 1275,
"rank": 25
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 57,
"coding": 68,
"writing": 57,
"agentic": 50,
"overall": 58
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 3,
"speed": 2
},
"popularity": 69,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.6-plus",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 36
},
"curated": true,
"pop_rank": 20
},
{
"id": "minimax/minimax-m2.5",
"slug": "minimax/minimax-m2.5-20260211",
"name": "MiniMax M2.5",
"vendor": "MiniMax",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...",
"created": 1770908502,
"created_human": "12 feb 2026",
"knowledge_cutoff": null,
"context_length": 204800,
"context_human": "205K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 0.9,
"blended_per_1m": 0.3375,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.34 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 203.7,
"ttft_seconds": 7.01
},
"benchmarks": {
"intelligence_index": 33.7,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 84.8,
"hle": 19.1,
"livecodebench": null,
"scicode": 42.6,
"aime": null,
"ifbench": 71.6,
"tau2": 95.3,
"terminalbench": 34.8,
"design_arena": {
"overall_elo": 1237,
"code_elo": 1257,
"count": 7,
"top": [
{
"category": "svg",
"elo": 1207,
"rank": 24
},
{
"category": "website",
"elo": 1265,
"rank": 27
},
{
"category": "codecategories",
"elo": 1257,
"rank": 30
},
{
"category": "3d",
"elo": 1248,
"rank": 31
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 59,
"writing": 48,
"agentic": 100,
"overall": 58
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 5,
"speed": 5
},
"popularity": 61,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/minimax/minimax-m2.5",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 41
},
"curated": true,
"pop_rank": 33
},
{
"id": "z-ai/glm-4.7",
"slug": "z-ai/glm-4.7-20251222",
"name": "GLM 4.7",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-4.7 is Z.ai’s flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...",
"created": 1766378014,
"created_human": "22 dec 2025",
"knowledge_cutoff": null,
"context_length": 202752,
"context_human": "203K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.4,
"completion_per_1m": 1.75,
"blended_per_1m": 0.7375,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.74 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 116.2,
"ttft_seconds": 0.56
},
"benchmarks": {
"intelligence_index": 33.8,
"coding_index": null,
"math_index": 95,
"agentic_index": null,
"mmlu_pro": 85.6,
"gpqa": 85.9,
"hle": 25.1,
"livecodebench": 89.4,
"scicode": 45.1,
"aime": 95,
"ifbench": 67.9,
"tau2": 95.9,
"terminalbench": 31.8,
"design_arena": {
"overall_elo": 1246,
"code_elo": 1268,
"count": 12,
"top": [
{
"category": "mobileapps",
"elo": 1190,
"rank": 16
},
{
"category": "androidnative",
"elo": 1123,
"rank": 17
},
{
"category": "godotgamedev",
"elo": 1131,
"rank": 17
},
{
"category": "asciiart",
"elo": 1212,
"rank": 19
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 62,
"writing": 48,
"agentic": 98,
"overall": 58
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 5,
"speed": 4
},
"popularity": 61,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-4.7",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 30
},
"curated": true,
"pop_rank": 34
},
{
"id": "openai/gpt-5.4-nano",
"slug": "openai/gpt-5.4-nano-20260317",
"name": "GPT-5.4 Nano",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...",
"created": 1773748187,
"created_human": "17 mrt 2026",
"knowledge_cutoff": "2025-08-31",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2,
"completion_per_1m": 1.25,
"blended_per_1m": 0.4625,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.46 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 166.9,
"ttft_seconds": 2.97
},
"benchmarks": {
"intelligence_index": 38.2,
"coding_index": 56.1,
"math_index": null,
"agentic_index": 27.5,
"mmlu_pro": null,
"gpqa": 81.7,
"hle": 26.5,
"livecodebench": null,
"scicode": 46.9,
"aime": null,
"ifbench": 75.9,
"tau2": 76,
"terminalbench": 60.7,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 55,
"coding": 70,
"writing": 55,
"agentic": 50,
"overall": 57
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 3,
"speed": 4
},
"popularity": 53,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.4-nano",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 42
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5",
"slug": "openai/gpt-5-2025-08-07",
"name": "GPT-5",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5 is OpenAI’s advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...",
"created": 1754587413,
"created_human": "7 aug 2025",
"knowledge_cutoff": "2024-09-30",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 107.7,
"ttft_seconds": 81.18
},
"benchmarks": {
"intelligence_index": 36.1,
"coding_index": null,
"math_index": 94.3,
"agentic_index": null,
"mmlu_pro": 87.1,
"gpqa": 85.4,
"hle": 26.5,
"livecodebench": 84.6,
"scicode": 42.9,
"aime": 94.3,
"ifbench": 73.1,
"tau2": 84.8,
"terminalbench": 32.6,
"design_arena": {
"overall_elo": 1223,
"code_elo": 1219,
"count": 8,
"top": [
{
"category": "svg",
"elo": 1244,
"rank": 13
},
{
"category": "dataviz",
"elo": 1281,
"rank": 15
},
{
"category": "asciiart",
"elo": 1186,
"rank": 27
},
{
"category": "gamedev",
"elo": 1253,
"rank": 31
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 52,
"coding": 48,
"writing": 52,
"agentic": 90,
"overall": 57
},
"stars": {
"intelligence": 3,
"coding": 2,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 60,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": true,
"pop_rank": 37
},
{
"id": "qwen/qwen3.7-plus",
"slug": "qwen/qwen3.7-plus-20260602",
"name": "Qwen3.7 Plus",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...",
"created": 1780491783,
"created_human": "3 jun 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.32,
"completion_per_1m": 1.28,
"blended_per_1m": 0.56,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.56 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 51.2,
"ttft_seconds": 1.72
},
"benchmarks": {
"intelligence_index": 39,
"coding_index": 55.9,
"math_index": null,
"agentic_index": 20.8,
"mmlu_pro": null,
"gpqa": 90,
"hle": 33.4,
"livecodebench": null,
"scicode": 45.5,
"aime": null,
"ifbench": 78,
"tau2": 93,
"terminalbench": 61,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 56,
"coding": 70,
"writing": 56,
"agentic": 38,
"overall": 56
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 2,
"speed": 2
},
"popularity": 59,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Programmeren",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.7-plus",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 39
},
"curated": true,
"pop_rank": 39
},
{
"id": "xiaomi/mimo-v2.5",
"slug": "xiaomi/mimo-v2.5-20260422",
"name": "MiMo-V2.5",
"vendor": "Xiaomi",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...",
"created": 1776874269,
"created_human": "22 apr 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.14,
"completion_per_1m": 0.28,
"blended_per_1m": 0.175,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1274,
"code_elo": 1304,
"count": 8,
"top": [
{
"category": "website",
"elo": 1305,
"rank": 11
},
{
"category": "uicomponent",
"elo": 1312,
"rank": 12
},
{
"category": "codecategories",
"elo": 1304,
"rank": 13
},
{
"category": "dataviz",
"elo": 1280,
"rank": 16
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 64,
"coding": 73,
"writing": 64,
"agentic": 0,
"overall": 56
},
"stars": {
"intelligence": 3,
"coding": 4,
"writing": 3,
"agentic": 0,
"speed": 3
},
"popularity": 58,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio",
"Voordelig in bulk"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/xiaomi/mimo-v2.5",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 72
},
"curated": true,
"pop_rank": 41
},
{
"id": "deepseek/deepseek-v3.2-exp",
"slug": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek V3.2 Exp",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
"created": 1759150481,
"created_human": "29 sep 2025",
"knowledge_cutoff": "2025-07-31",
"context_length": 163840,
"context_human": "164K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.27,
"completion_per_1m": 0.41,
"blended_per_1m": 0.305,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.31 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 33.4,
"coding_index": null,
"math_index": 92,
"agentic_index": null,
"mmlu_pro": 86.2,
"gpqa": 84,
"hle": 22.2,
"livecodebench": 86.2,
"scicode": 38.9,
"aime": 92,
"ifbench": 60.7,
"tau2": 90.6,
"terminalbench": 35.6,
"design_arena": {
"overall_elo": 1198,
"code_elo": 1221,
"count": 7,
"top": [
{
"category": "3d",
"elo": 1227,
"rank": 36
},
{
"category": "uicomponent",
"elo": 1220,
"rank": 39
},
{
"category": "codecategories",
"elo": 1221,
"rank": 40
},
{
"category": "gamedev",
"elo": 1212,
"rank": 42
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 49,
"writing": 48,
"agentic": 97,
"overall": 56
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 5,
"speed": 3
},
"popularity": 57,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-v3.2-exp",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 43
},
"curated": true,
"pop_rank": 45
},
{
"id": "nvidia/nemotron-3-ultra-550b-a55b:free",
"slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604",
"name": "Nemotron 3 Ultra (free)",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
"created": 1780551208,
"created_human": "4 jun 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 37.8,
"coding_index": 49.3,
"math_index": null,
"agentic_index": 27.4,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1163,
"code_elo": 1166,
"count": 7,
"top": [
{
"category": "3d",
"elo": 1209,
"rank": 41
},
{
"category": "svg",
"elo": 1134,
"rank": 44
},
{
"category": "gamedev",
"elo": 1196,
"rank": 54
},
{
"category": "uicomponent",
"elo": 1158,
"rank": 58
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 62,
"writing": 54,
"agentic": 50,
"overall": 55
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 3,
"speed": 2
},
"popularity": 56,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Lange documenten",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"long-context",
"free"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 100
},
"curated": true,
"pop_rank": 49
},
{
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"slug": "nvidia/nemotron-3-ultra-550b-a55b-20260604",
"name": "Nemotron 3 Ultra",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
"created": 1780551208,
"created_human": "4 jun 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.5,
"completion_per_1m": 2.2,
"blended_per_1m": 0.925,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.93 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 37.8,
"coding_index": 49.3,
"math_index": null,
"agentic_index": 27.4,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1163,
"code_elo": 1166,
"count": 7,
"top": [
{
"category": "3d",
"elo": 1209,
"rank": 41
},
{
"category": "svg",
"elo": 1134,
"rank": 44
},
{
"category": "gamedev",
"elo": 1196,
"rank": 54
},
{
"category": "uicomponent",
"elo": 1158,
"rank": 58
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 62,
"writing": 54,
"agentic": 50,
"overall": 55
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 3,
"speed": 2
},
"popularity": 56,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Lange documenten"
],
"categories": [
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 31
},
"curated": true,
"pop_rank": 50
},
{
"id": "qwen/qwen3.6-27b",
"slug": "qwen/qwen3.6-27b-20260422",
"name": "Qwen3.6 27B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...",
"created": 1777255064,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2885,
"completion_per_1m": 3.17,
"blended_per_1m": 1.0089,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.0 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 64.2,
"ttft_seconds": 1.35
},
"benchmarks": {
"intelligence_index": 37.1,
"coding_index": 53.7,
"math_index": null,
"agentic_index": 27,
"mmlu_pro": null,
"gpqa": 84.2,
"hle": 21.6,
"livecodebench": null,
"scicode": 39.8,
"aime": null,
"ifbench": 67.6,
"tau2": 94.2,
"terminalbench": 60.7,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 53,
"coding": 67,
"writing": 53,
"agentic": 49,
"overall": 55
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 2,
"speed": 3
},
"popularity": 55,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.6-27b",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 30
},
"curated": false,
"pop_rank": null
},
{
"id": "minimax/minimax-m2.7",
"slug": "minimax/minimax-m2.7-20260318",
"name": "MiniMax M2.7",
"vendor": "MiniMax",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through…",
"created": 1773836697,
"created_human": "18 mrt 2026",
"knowledge_cutoff": null,
"context_length": 204800,
"context_human": "205K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.24,
"completion_per_1m": 0.96,
"blended_per_1m": 0.42,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.42 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 47.6,
"ttft_seconds": 1.68
},
"benchmarks": {
"intelligence_index": 38.1,
"coding_index": 52.6,
"math_index": null,
"agentic_index": 25.6,
"mmlu_pro": null,
"gpqa": 87.4,
"hle": 28.1,
"livecodebench": null,
"scicode": 47,
"aime": null,
"ifbench": 75.7,
"tau2": 84.8,
"terminalbench": 55.4,
"design_arena": {
"overall_elo": 1254,
"code_elo": 1282,
"count": 8,
"top": [
{
"category": "dataviz",
"elo": 1272,
"rank": 19
},
{
"category": "website",
"elo": 1287,
"rank": 20
},
{
"category": "codecategories",
"elo": 1282,
"rank": 22
},
{
"category": "gamedev",
"elo": 1275,
"rank": 23
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 66,
"writing": 54,
"agentic": 47,
"overall": 55
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 2,
"speed": 2
},
"popularity": 67,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Zelfstandige taken",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/minimax/minimax-m2.7",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 43
},
"curated": true,
"pop_rank": 27
},
{
"id": "openai/gpt-5.2-chat",
"slug": "openai/gpt-5.2-chat-20251211",
"name": "GPT-5.2 Chat",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...",
"created": 1765389783,
"created_human": "10 dec 2025",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.75,
"completion_per_1m": 14,
"blended_per_1m": 4.8125,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.8 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 86.8,
"ttft_seconds": 77.21
},
"benchmarks": {
"intelligence_index": 42.2,
"coding_index": null,
"math_index": 99,
"agentic_index": null,
"mmlu_pro": 87.4,
"gpqa": 90.3,
"hle": 35.4,
"livecodebench": 88.9,
"scicode": 52.1,
"aime": 99,
"ifbench": 75.4,
"tau2": 84.8,
"terminalbench": 47,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 60,
"coding": 0,
"writing": 63,
"agentic": 100,
"overall": 55
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 50,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.2-chat",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-v3.2",
"slug": "deepseek/deepseek-v3.2-20251201",
"name": "DeepSeek V3.2",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
"created": 1764594642,
"created_human": "1 dec 2025",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2288,
"completion_per_1m": 0.3432,
"blended_per_1m": 0.2574,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.26 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 33.4,
"coding_index": null,
"math_index": 92,
"agentic_index": null,
"mmlu_pro": 86.2,
"gpqa": 84,
"hle": 22.2,
"livecodebench": 86.2,
"scicode": 38.9,
"aime": 92,
"ifbench": 60.7,
"tau2": 90.6,
"terminalbench": 35.6,
"design_arena": {
"overall_elo": 1183,
"code_elo": 1214,
"count": 8,
"top": [
{
"category": "3d",
"elo": 1212,
"rank": 40
},
{
"category": "asciiart",
"elo": 1126,
"rank": 41
},
{
"category": "uicomponent",
"elo": 1206,
"rank": 46
},
{
"category": "website",
"elo": 1218,
"rank": 46
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 47,
"writing": 48,
"agentic": 97,
"overall": 55
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 5,
"speed": 3
},
"popularity": 58,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-v3.2",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 46
},
"curated": true,
"pop_rank": 42
},
{
"id": "openai/gpt-5.1-codex",
"slug": "openai/gpt-5.1-codex-20251113",
"name": "GPT-5.1-Codex",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
"created": 1763060298,
"created_human": "13 nov 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 208.9,
"ttft_seconds": 5.76
},
"benchmarks": {
"intelligence_index": 34.7,
"coding_index": null,
"math_index": 95.7,
"agentic_index": null,
"mmlu_pro": 86,
"gpqa": 86,
"hle": 23.4,
"livecodebench": 84.9,
"scicode": 40.2,
"aime": 95.7,
"ifbench": 70,
"tau2": 83,
"terminalbench": 34.8,
"design_arena": {
"overall_elo": 1207,
"code_elo": 1201,
"count": 7,
"top": [
{
"category": "mobileapps",
"elo": 1203,
"rank": 14
},
{
"category": "fullstack",
"elo": 1092,
"rank": 23
},
{
"category": "webapps",
"elo": 1087,
"rank": 24
},
{
"category": "dataviz",
"elo": 1217,
"rank": 39
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 50,
"coding": 43,
"writing": 50,
"agentic": 91,
"overall": 55
},
"stars": {
"intelligence": 3,
"coding": 2,
"writing": 3,
"agentic": 5,
"speed": 5
},
"popularity": 58,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.1-codex",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": true,
"pop_rank": 43
},
{
"id": "nex-agi/nex-n2-pro",
"slug": "nex-agi/nex-n2-pro",
"name": "Nex-N2-Pro",
"vendor": "Nex-agi",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...",
"created": 1780937140,
"created_human": "8 jun 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 1,
"blended_per_1m": 0.4375,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.44 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1272,
"code_elo": 1279,
"count": 6,
"top": [
{
"category": "3d",
"elo": 1320,
"rank": 12
},
{
"category": "gamedev",
"elo": 1278,
"rank": 22
},
{
"category": "codecategories",
"elo": 1279,
"rank": 24
},
{
"category": "dataviz",
"elo": 1252,
"rank": 27
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 63,
"coding": 65,
"writing": 63,
"agentic": 0,
"overall": 54
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 0,
"speed": 2
},
"popularity": 60,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Programmeren",
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/nex-agi/nex-n2-pro",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 49
},
"curated": true,
"pop_rank": 38
},
{
"id": "minimax/minimax-m2.1",
"slug": "minimax/minimax-m2.1",
"name": "MiniMax M2.1",
"vendor": "MiniMax",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...",
"created": 1766454997,
"created_human": "23 dec 2025",
"knowledge_cutoff": null,
"context_length": 204800,
"context_human": "205K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.29,
"completion_per_1m": 0.95,
"blended_per_1m": 0.455,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.46 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 223.4,
"ttft_seconds": 8.19
},
"benchmarks": {
"intelligence_index": 31.4,
"coding_index": null,
"math_index": 82.7,
"agentic_index": null,
"mmlu_pro": 87.5,
"gpqa": 83,
"hle": 22.2,
"livecodebench": 81,
"scicode": 40.7,
"aime": 82.7,
"ifbench": 69.9,
"tau2": 85.4,
"terminalbench": 28.8,
"design_arena": {
"overall_elo": 1235,
"code_elo": 1240,
"count": 7,
"top": [
{
"category": "uicomponent",
"elo": 1277,
"rank": 23
},
{
"category": "dataviz",
"elo": 1249,
"rank": 28
},
{
"category": "svg",
"elo": 1188,
"rank": 31
},
{
"category": "3d",
"elo": 1244,
"rank": 32
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 45,
"coding": 54,
"writing": 45,
"agentic": 88,
"overall": 53
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 4,
"speed": 5
},
"popularity": 56,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/minimax/minimax-m2.1",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 34
},
"curated": false,
"pop_rank": null
},
{
"id": "x-ai/grok-4.3",
"slug": "x-ai/grok-4.3-20260430",
"name": "Grok 4.3",
"vendor": "xAI (Grok)",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...",
"created": 1777591821,
"created_human": "30 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 2.5,
"blended_per_1m": 1.5625,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.6 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 163.8,
"ttft_seconds": 19.22
},
"benchmarks": {
"intelligence_index": 37.6,
"coding_index": 42.2,
"math_index": null,
"agentic_index": 24.1,
"mmlu_pro": null,
"gpqa": 90.1,
"hle": 35,
"livecodebench": null,
"scicode": 47.3,
"aime": null,
"ifbench": 81.3,
"tau2": 97.7,
"terminalbench": 39.7,
"design_arena": {
"overall_elo": 1221,
"code_elo": 1247,
"count": 21,
"top": [
{
"category": "pptxslides",
"elo": 1071,
"rank": 9
},
{
"category": "python-pptxslides",
"elo": 1072,
"rank": 9
},
{
"category": "agenticgamedev",
"elo": 1033,
"rank": 10
},
{
"category": "agentichtmlslides",
"elo": 1066,
"rank": 10
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 53,
"writing": 54,
"agentic": 44,
"overall": 52
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 2,
"speed": 4
},
"popularity": 75,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/x-ai/grok-4.3",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": true,
"pop_rank": 14
},
{
"id": "qwen/qwen3.6-max-preview",
"slug": "qwen/qwen3.6-max-preview-20260420",
"name": "Qwen3.6 Max Preview",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...",
"created": 1777260242,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.04,
"completion_per_1m": 6.24,
"blended_per_1m": 2.34,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$2.3 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 45.2,
"ttft_seconds": 1.86
},
"benchmarks": {
"intelligence_index": 40,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 88.8,
"hle": 28.9,
"livecodebench": null,
"scicode": 46.9,
"aime": null,
"ifbench": 76.6,
"tau2": 95.9,
"terminalbench": 43.9,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 57,
"coding": 0,
"writing": 57,
"agentic": 100,
"overall": 52
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 2
},
"popularity": 57,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Zelfstandige taken"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.6-max-preview",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 23
},
"curated": true,
"pop_rank": 46
},
{
"id": "openai/gpt-5.2-codex",
"slug": "openai/gpt-5.2-codex-20260114",
"name": "GPT-5.2-Codex",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
"created": 1768409315,
"created_human": "14 jan 2026",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.75,
"completion_per_1m": 14,
"blended_per_1m": 4.8125,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.8 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 148.1,
"ttft_seconds": 1.41
},
"benchmarks": {
"intelligence_index": 40.1,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 89.9,
"hle": 33.5,
"livecodebench": null,
"scicode": 54.6,
"aime": null,
"ifbench": 77.6,
"tau2": 92.1,
"terminalbench": 37.1,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 5,
"top": [
{
"category": "godotgamedev",
"elo": 1187,
"rank": 12
},
{
"category": "androidnative",
"elo": 1176,
"rank": 13
},
{
"category": "webapps",
"elo": 1127,
"rank": 22
},
{
"category": "mobileapps",
"elo": 1173,
"rank": 24
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 57,
"coding": 0,
"writing": 57,
"agentic": 99,
"overall": 52
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 4
},
"popularity": 61,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.2-codex",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": true,
"pop_rank": 35
},
{
"id": "openai/gpt-5.1-chat",
"slug": "openai/gpt-5.1-chat-20251113",
"name": "GPT-5.1 Chat",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...",
"created": 1763060302,
"created_human": "13 nov 2025",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 104.9,
"ttft_seconds": 30.63
},
"benchmarks": {
"intelligence_index": 38.9,
"coding_index": null,
"math_index": 94,
"agentic_index": null,
"mmlu_pro": 87,
"gpqa": 87.3,
"hle": 26.5,
"livecodebench": 86.8,
"scicode": 43.3,
"aime": 94,
"ifbench": 72.9,
"tau2": 81.9,
"terminalbench": 45.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 56,
"coding": 0,
"writing": 59,
"agentic": 98,
"overall": 52
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 48,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.1-chat",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "anthropic/claude-opus-4.6-fast",
"slug": "anthropic/claude-4.6-opus-fast-20260407",
"name": "Claude Opus 4.6 (Fast)",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Fast-mode variant of Opus 4.6 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode",
"created": 1775592472,
"created_human": "7 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 30,
"completion_per_1m": 150,
"blended_per_1m": 60,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$60 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 60.7,
"ttft_seconds": 1.7
},
"benchmarks": {
"intelligence_index": 37.8,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 84,
"hle": 18.6,
"livecodebench": null,
"scicode": 45.7,
"aime": null,
"ifbench": 44.6,
"tau2": 84.8,
"terminalbench": 48.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 54,
"coding": 0,
"writing": 54,
"agentic": 100,
"overall": 50
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 54,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.6-fast",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 6
},
"curated": false,
"pop_rank": null
},
{
"id": "moonshotai/kimi-k2-thinking",
"slug": "moonshotai/kimi-k2-thinking-20251106",
"name": "Kimi K2 Thinking",
"vendor": "Moonshot AI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Kimi K2 Thinking is Moonshot AI’s advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...",
"created": 1762440622,
"created_human": "6 nov 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.6,
"completion_per_1m": 2.5,
"blended_per_1m": 1.075,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.1 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 142.9,
"ttft_seconds": 0.9
},
"benchmarks": {
"intelligence_index": 32.7,
"coding_index": 21,
"math_index": 94.7,
"agentic_index": null,
"mmlu_pro": 84.8,
"gpqa": 83.8,
"hle": 22.3,
"livecodebench": 85.3,
"scicode": 42.4,
"aime": 94.7,
"ifbench": 68.1,
"tau2": 93,
"terminalbench": 31.1,
"design_arena": {
"overall_elo": 1156,
"code_elo": null,
"count": 1,
"top": [
{
"category": "website",
"elo": 1156,
"rank": 70
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 47,
"coding": 26,
"writing": 47,
"agentic": 95,
"overall": 50
},
"stars": {
"intelligence": 2,
"coding": 1,
"writing": 2,
"agentic": 5,
"speed": 4
},
"popularity": 52,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/moonshotai/kimi-k2-thinking",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 26
},
"curated": false,
"pop_rank": null
},
{
"id": "x-ai/grok-4.20",
"slug": "x-ai/grok-4.20-20260309",
"name": "Grok 4.20",
"vendor": "xAI (Grok)",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...",
"created": 1774979019,
"created_human": "31 mrt 2026",
"knowledge_cutoff": "2025-09-01",
"context_length": 2000000,
"context_human": "2M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 2.5,
"blended_per_1m": 1.5625,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.6 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 267.3,
"ttft_seconds": 10.9
},
"benchmarks": {
"intelligence_index": 37,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 91.1,
"hle": 32.2,
"livecodebench": null,
"scicode": 45.6,
"aime": null,
"ifbench": 81.2,
"tau2": 93,
"terminalbench": 37.9,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 53,
"coding": 0,
"writing": 53,
"agentic": 100,
"overall": 49
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 5
},
"popularity": 53,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/x-ai/grok-4.20",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": false,
"pop_rank": null
},
{
"id": "kwaipilot/kat-coder-pro-v2",
"slug": "kwaipilot/kat-coder-pro-v2-20260327",
"name": "KAT-Coder-Pro V2",
"vendor": "Kwaipilot",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "KAT-Coder-Pro V2 is the high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...",
"created": 1774649310,
"created_human": "27 mrt 2026",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 1.2,
"blended_per_1m": 0.525,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.53 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 117.5,
"ttft_seconds": 0.95
},
"benchmarks": {
"intelligence_index": 35.4,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 85.5,
"hle": 16,
"livecodebench": null,
"scicode": 38.3,
"aime": null,
"ifbench": 66.7,
"tau2": 89.5,
"terminalbench": 49.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 51,
"coding": 0,
"writing": 54,
"agentic": 100,
"overall": 49
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 4
},
"popularity": 52,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/kwaipilot/kat-coder-pro-v2",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 37
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-397b-a17b",
"slug": "qwen/qwen3.5-397b-a17b-20260216",
"name": "Qwen3.5 397B A17B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...",
"created": 1771223018,
"created_human": "16 feb 2026",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.385,
"completion_per_1m": 2.45,
"blended_per_1m": 0.9013,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.90 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 52,
"ttft_seconds": 1.68
},
"benchmarks": {
"intelligence_index": 33.7,
"coding_index": 48.2,
"math_index": null,
"agentic_index": 19.8,
"mmlu_pro": null,
"gpqa": 89.3,
"hle": 27.3,
"livecodebench": null,
"scicode": 42,
"aime": null,
"ifbench": 78.8,
"tau2": 95.6,
"terminalbench": 51.3,
"design_arena": {
"overall_elo": 1220,
"code_elo": 1230,
"count": 7,
"top": [
{
"category": "svg",
"elo": 1198,
"rank": 28
},
{
"category": "3d",
"elo": 1239,
"rank": 33
},
{
"category": "codecategories",
"elo": 1230,
"rank": 35
},
{
"category": "website",
"elo": 1234,
"rank": 37
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 60,
"writing": 48,
"agentic": 36,
"overall": 49
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 2,
"speed": 2
},
"popularity": 61,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Programmeren",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-397b-a17b",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 28
},
"curated": true,
"pop_rank": 36
},
{
"id": "openai/gpt-5-mini",
"slug": "openai/gpt-5-mini-2025-08-07",
"name": "GPT-5 Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....",
"created": 1754587407,
"created_human": "7 aug 2025",
"knowledge_cutoff": "2024-05-31",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 2,
"blended_per_1m": 0.6875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.69 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 89.6,
"ttft_seconds": 90.68
},
"benchmarks": {
"intelligence_index": 33,
"coding_index": null,
"math_index": 90.7,
"agentic_index": null,
"mmlu_pro": 83.7,
"gpqa": 82.8,
"hle": 19.7,
"livecodebench": 83.8,
"scicode": 39.2,
"aime": 90.7,
"ifbench": 75.4,
"tau2": 68.4,
"terminalbench": 33.3,
"design_arena": {
"overall_elo": 1160,
"code_elo": 1165,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1167,
"rank": 34
},
{
"category": "svg",
"elo": 1146,
"rank": 40
},
{
"category": "gamedev",
"elo": 1197,
"rank": 53
},
{
"category": "uicomponent",
"elo": 1159,
"rank": 57
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 47,
"coding": 33,
"writing": 47,
"agentic": 78,
"overall": 49
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 4,
"speed": 3
},
"popularity": 58,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5-mini",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 31
},
"curated": true,
"pop_rank": 44
},
{
"id": "qwen/qwen3-max",
"slug": "qwen/qwen3-max",
"name": "Qwen3 Max",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...",
"created": 1758662808,
"created_human": "23 sep 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.78,
"completion_per_1m": 3.9,
"blended_per_1m": 1.56,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.6 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 31.7,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 86.1,
"hle": 26.2,
"livecodebench": null,
"scicode": 43.1,
"aime": null,
"ifbench": 70.7,
"tau2": 83.6,
"terminalbench": 24.2,
"design_arena": {
"overall_elo": 1144,
"code_elo": 1160,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1173,
"rank": 33
},
{
"category": "svg",
"elo": 1067,
"rank": 58
},
{
"category": "gamedev",
"elo": 1162,
"rank": 61
},
{
"category": "3d",
"elo": 1152,
"rank": 63
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 45,
"coding": 31,
"writing": 45,
"agentic": 83,
"overall": 48
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 4,
"speed": 2
},
"popularity": 57,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-max",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 21
},
"curated": true,
"pop_rank": 47
},
{
"id": "openai/gpt-5-codex",
"slug": "openai/gpt-5-codex",
"name": "GPT-5 Codex",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
"created": 1758643403,
"created_human": "23 sep 2025",
"knowledge_cutoff": "2024-09-30",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 208.4,
"ttft_seconds": 10.82
},
"benchmarks": {
"intelligence_index": 36.1,
"coding_index": null,
"math_index": 98.7,
"agentic_index": null,
"mmlu_pro": 86.5,
"gpqa": 83.7,
"hle": 25.6,
"livecodebench": 84,
"scicode": 40.9,
"aime": 98.7,
"ifbench": 74.1,
"tau2": 86.8,
"terminalbench": 37.9,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 1,
"top": [
{
"category": "mobileapps",
"elo": 1132,
"rank": 28
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 52,
"coding": 0,
"writing": 52,
"agentic": 96,
"overall": 48
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 5
},
"popularity": 54,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5-codex",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5-chat",
"slug": "openai/gpt-5-chat-2025-08-07",
"name": "GPT-5 Chat",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.",
"created": 1754587837,
"created_human": "7 aug 2025",
"knowledge_cutoff": "2024-09-30",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 107.7,
"ttft_seconds": 81.18
},
"benchmarks": {
"intelligence_index": 36.1,
"coding_index": null,
"math_index": 94.3,
"agentic_index": null,
"mmlu_pro": 87.1,
"gpqa": 85.4,
"hle": 26.5,
"livecodebench": 84.6,
"scicode": 42.9,
"aime": 94.3,
"ifbench": 73.1,
"tau2": 84.8,
"terminalbench": 32.6,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 52,
"coding": 0,
"writing": 55,
"agentic": 90,
"overall": 48
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 5,
"speed": 3
},
"popularity": 46,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Schrijven & e-mails",
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5-chat",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-122b-a10b",
"slug": "qwen/qwen3.5-122b-a10b-20260224",
"name": "Qwen3.5-122B-A10B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...",
"created": 1772053789,
"created_human": "25 feb 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.26,
"completion_per_1m": 2.08,
"blended_per_1m": 0.715,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.72 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 148.6,
"ttft_seconds": 1.08
},
"benchmarks": {
"intelligence_index": 32.3,
"coding_index": 45.7,
"math_index": null,
"agentic_index": 20.7,
"mmlu_pro": null,
"gpqa": 85.7,
"hle": 23.4,
"livecodebench": null,
"scicode": 42,
"aime": null,
"ifbench": 75.7,
"tau2": 93.6,
"terminalbench": 47.6,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 46,
"coding": 57,
"writing": 46,
"agentic": 38,
"overall": 47
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 2,
"speed": 4
},
"popularity": 48,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-122b-a10b",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": false,
"pop_rank": null
},
{
"id": "minimax/minimax-m2",
"slug": "minimax/minimax-m2",
"name": "MiniMax M2",
"vendor": "MiniMax",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasonin…",
"created": 1761252093,
"created_human": "23 okt 2025",
"knowledge_cutoff": null,
"context_length": 204800,
"context_human": "205K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.255,
"completion_per_1m": 1,
"blended_per_1m": 0.4413,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.44 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 126.6,
"ttft_seconds": 1.34
},
"benchmarks": {
"intelligence_index": 28.3,
"coding_index": null,
"math_index": 78.3,
"agentic_index": null,
"mmlu_pro": 82,
"gpqa": 77.7,
"hle": 12.5,
"livecodebench": 82.6,
"scicode": 36.1,
"aime": 78.3,
"ifbench": 72.3,
"tau2": 86.8,
"terminalbench": 25.8,
"design_arena": {
"overall_elo": 1180,
"code_elo": 1185,
"count": 7,
"top": [
{
"category": "svg",
"elo": 1156,
"rank": 38
},
{
"category": "3d",
"elo": 1176,
"rank": 52
},
{
"category": "uicomponent",
"elo": 1190,
"rank": 52
},
{
"category": "dataviz",
"elo": 1183,
"rank": 54
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 40,
"coding": 39,
"writing": 40,
"agentic": 87,
"overall": 47
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 4,
"speed": 4
},
"popularity": 54,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/minimax/minimax-m2",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 31
},
"curated": false,
"pop_rank": null
},
{
"id": "moonshotai/kimi-k2",
"slug": "moonshotai/kimi-k2",
"name": "Kimi K2 0711",
"vendor": "Moonshot AI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...",
"created": 1752263252,
"created_human": "11 jul 2025",
"knowledge_cutoff": "2024-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.57,
"completion_per_1m": 2.3,
"blended_per_1m": 1.0025,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.0 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 142.9,
"ttft_seconds": 0.9
},
"benchmarks": {
"intelligence_index": 32.7,
"coding_index": null,
"math_index": 94.7,
"agentic_index": null,
"mmlu_pro": 84.8,
"gpqa": 83.8,
"hle": 22.3,
"livecodebench": 85.3,
"scicode": 42.4,
"aime": 94.7,
"ifbench": 68.1,
"tau2": 93,
"terminalbench": 31.1,
"design_arena": {
"overall_elo": 1073,
"code_elo": 1084,
"count": 5,
"top": [
{
"category": "uicomponent",
"elo": 1085,
"rank": 75
},
{
"category": "codecategories",
"elo": 1084,
"rank": 82
},
{
"category": "dataviz",
"elo": 1061,
"rank": 84
},
{
"category": "website",
"elo": 1094,
"rank": 85
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 47,
"coding": 10,
"writing": 49,
"agentic": 95,
"overall": 47
},
"stars": {
"intelligence": 2,
"coding": 1,
"writing": 2,
"agentic": 5,
"speed": 4
},
"popularity": 55,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/moonshotai/kimi-k2",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 26
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.6-35b-a3b",
"slug": "qwen/qwen3.6-35b-a3b-20260415",
"name": "Qwen3.6 35B A3B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...",
"created": 1777260255,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.14,
"completion_per_1m": 1,
"blended_per_1m": 0.355,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.36 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 178.7,
"ttft_seconds": 1.31
},
"benchmarks": {
"intelligence_index": 31.6,
"coding_index": 41.9,
"math_index": null,
"agentic_index": 21.4,
"mmlu_pro": null,
"gpqa": 84.1,
"hle": 20.2,
"livecodebench": null,
"scicode": 35.8,
"aime": null,
"ifbench": 64.4,
"tau2": 95.3,
"terminalbench": 44.9,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 45,
"coding": 52,
"writing": 45,
"agentic": 39,
"overall": 46
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 2,
"speed": 4
},
"popularity": 52,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.6-35b-a3b",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 38
},
"curated": false,
"pop_rank": null
},
{
"id": "tencent/hy3-preview",
"slug": "tencent/hy3-preview-20260421",
"name": "Hy3 preview",
"vendor": "Tencent",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...",
"created": 1776878150,
"created_human": "22 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.063,
"completion_per_1m": 0.21,
"blended_per_1m": 0.0998,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.10 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 109.7,
"ttft_seconds": 2.31
},
"benchmarks": {
"intelligence_index": 33.6,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 86.7,
"hle": 25.5,
"livecodebench": null,
"scicode": 41.2,
"aime": null,
"ifbench": 63.1,
"tau2": 92.7,
"terminalbench": 34.1,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 0,
"writing": 48,
"agentic": 98,
"overall": 46
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 5,
"speed": 3
},
"popularity": 53,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/tencent/hy3-preview",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 67
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-27b",
"slug": "qwen/qwen3.5-27b-20260224",
"name": "Qwen3.5-27B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...",
"created": 1772053810,
"created_human": "25 feb 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.195,
"completion_per_1m": 1.56,
"blended_per_1m": 0.5363,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.54 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 86.8,
"ttft_seconds": 1.47
},
"benchmarks": {
"intelligence_index": 33.8,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 85.8,
"hle": 22.2,
"livecodebench": null,
"scicode": 39.5,
"aime": null,
"ifbench": 75.6,
"tau2": 93.9,
"terminalbench": 32.6,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 0,
"writing": 48,
"agentic": 97,
"overall": 46
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 5,
"speed": 3
},
"popularity": 49,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-27b",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 34
},
"curated": false,
"pop_rank": null
},
{
"id": "z-ai/glm-4.7-flash",
"slug": "z-ai/glm-4.7-flash-20260119",
"name": "GLM 4.7 Flash",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...",
"created": 1768833913,
"created_human": "19 jan 2026",
"knowledge_cutoff": null,
"context_length": 202752,
"context_human": "203K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.06,
"completion_per_1m": 0.4,
"blended_per_1m": 0.145,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.15 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 83.4,
"ttft_seconds": 0.99
},
"benchmarks": {
"intelligence_index": 22.9,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 58.1,
"hle": 7.1,
"livecodebench": null,
"scicode": 33.7,
"aime": null,
"ifbench": 60.8,
"tau2": 98.8,
"terminalbench": 22,
"design_arena": {
"overall_elo": 1198,
"code_elo": 1228,
"count": 7,
"top": [
{
"category": "uicomponent",
"elo": 1262,
"rank": 26
},
{
"category": "codecategories",
"elo": 1228,
"rank": 36
},
{
"category": "website",
"elo": 1237,
"rank": 36
},
{
"category": "3d",
"elo": 1199,
"rank": 45
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 33,
"coding": 51,
"writing": 33,
"agentic": 93,
"overall": 46
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 5,
"speed": 3
},
"popularity": 52,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-4.7-flash",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 40
},
"curated": false,
"pop_rank": null
},
{
"id": "inclusionai/ring-2.6-1t",
"slug": "inclusionai/ring-2.6-1t-20260508",
"name": "Ring-2.6-1T",
"vendor": "inclusionAI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...",
"created": 1778247440,
"created_human": "8 mei 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.075,
"completion_per_1m": 0.625,
"blended_per_1m": 0.2125,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.21 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 135.7,
"ttft_seconds": 1.91
},
"benchmarks": {
"intelligence_index": 30.6,
"coding_index": 42.8,
"math_index": null,
"agentic_index": 18.9,
"mmlu_pro": null,
"gpqa": 85.7,
"hle": 18.3,
"livecodebench": null,
"scicode": 42.4,
"aime": null,
"ifbench": 44.6,
"tau2": 92.4,
"terminalbench": 43.1,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 44,
"coding": 54,
"writing": 44,
"agentic": 34,
"overall": 45
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 2,
"speed": 4
},
"popularity": 52,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Voordelig in bulk"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/inclusionai/ring-2.6-1t",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 46
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-medium-3-5",
"slug": "mistralai/mistral-medium-3.5-20260430",
"name": "Mistral Medium 3.5",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...",
"created": 1777570439,
"created_human": "30 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.5,
"completion_per_1m": 7.5,
"blended_per_1m": 3,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.0 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 140.8,
"ttft_seconds": 0.74
},
"benchmarks": {
"intelligence_index": 29.9,
"coding_index": 46.9,
"math_index": null,
"agentic_index": 19,
"mmlu_pro": null,
"gpqa": 74.8,
"hle": 12.8,
"livecodebench": null,
"scicode": 39.6,
"aime": null,
"ifbench": 68.8,
"tau2": 94.2,
"terminalbench": 50.6,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 43,
"coding": 59,
"writing": 43,
"agentic": 35,
"overall": 45
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 2,
"speed": 4
},
"popularity": 51,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-medium-3-5",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 15
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-3.1-flash-image-preview",
"slug": "google/gemini-3.1-flash-image-preview-20260226",
"name": "Nano Banana 2 (Gemini 3.1 Flash Image Preview)",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...",
"created": 1772119558,
"created_human": "26 feb 2026",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": true,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.5,
"completion_per_1m": 3,
"blended_per_1m": 1.125,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.1 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1293,
"code_elo": null,
"count": 3,
"top": [
{
"category": "graphicdesign",
"elo": 1293,
"rank": 1
},
{
"category": "image",
"elo": 1304,
"rank": 1
},
{
"category": "logo",
"elo": 1282,
"rank": 1
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 69,
"coding": 0,
"writing": 69,
"agentic": 0,
"overall": 45
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 0,
"speed": 5
},
"popularity": 53,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Chat & klantenservice",
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3.1-flash-image-preview",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 37
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5.1-codex-mini",
"slug": "openai/gpt-5.1-codex-mini-20251113",
"name": "GPT-5.1-Codex-Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex",
"created": 1763057820,
"created_human": "13 nov 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 2,
"blended_per_1m": 0.6875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.69 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 214.9,
"ttft_seconds": 4.12
},
"benchmarks": {
"intelligence_index": 30.6,
"coding_index": null,
"math_index": 91.7,
"agentic_index": null,
"mmlu_pro": 82,
"gpqa": 81.3,
"hle": 16.9,
"livecodebench": 83.6,
"scicode": 42.6,
"aime": 91.7,
"ifbench": 67.9,
"tau2": 62.9,
"terminalbench": 33.3,
"design_arena": {
"overall_elo": 1123,
"code_elo": 1144,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1149,
"rank": 38
},
{
"category": "gamedev",
"elo": 1160,
"rank": 63
},
{
"category": "svg",
"elo": 1033,
"rank": 64
},
{
"category": "uicomponent",
"elo": 1134,
"rank": 65
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 44,
"coding": 27,
"writing": 44,
"agentic": 74,
"overall": 45
},
"stars": {
"intelligence": 2,
"coding": 1,
"writing": 2,
"agentic": 4,
"speed": 5
},
"popularity": 56,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.1-codex-mini",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-9b",
"slug": "qwen/qwen3.5-9b-20260310",
"name": "Qwen3.5-9B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...",
"created": 1773152396,
"created_human": "10 mrt 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.15,
"blended_per_1m": 0.1125,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.11 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 62.1,
"ttft_seconds": 1.12
},
"benchmarks": {
"intelligence_index": 25,
"coding_index": 28.7,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 80.6,
"hle": 13.3,
"livecodebench": null,
"scicode": 27.5,
"aime": null,
"ifbench": 66.7,
"tau2": 86.8,
"terminalbench": 29.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 36,
"coding": 36,
"writing": 36,
"agentic": 89,
"overall": 44
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 4,
"speed": 3
},
"popularity": 44,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-9b",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 48
},
"curated": false,
"pop_rank": null
},
{
"id": "z-ai/glm-4.6",
"slug": "z-ai/glm-4.6",
"name": "GLM 4.6",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...",
"created": 1759235576,
"created_human": "30 sep 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 202752,
"context_human": "203K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.43,
"completion_per_1m": 1.74,
"blended_per_1m": 0.7575,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.76 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 46.6,
"ttft_seconds": 1.34
},
"benchmarks": {
"intelligence_index": 25.1,
"coding_index": null,
"math_index": 86,
"agentic_index": null,
"mmlu_pro": 82.9,
"gpqa": 78,
"hle": 13.3,
"livecodebench": 69.5,
"scicode": 38.4,
"aime": 86,
"ifbench": 43.4,
"tau2": 70.5,
"terminalbench": 25,
"design_arena": {
"overall_elo": 1206,
"code_elo": 1216,
"count": 11,
"top": [
{
"category": "godotgamedev",
"elo": 1218,
"rank": 8
},
{
"category": "androidnative",
"elo": 1094,
"rank": 19
},
{
"category": "mobileapps",
"elo": 1186,
"rank": 20
},
{
"category": "fullstack",
"elo": 1099,
"rank": 22
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 36,
"coding": 47,
"writing": 36,
"agentic": 73,
"overall": 44
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 4,
"speed": 2
},
"popularity": 55,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-4.6",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 22
},
"curated": false,
"pop_rank": null
},
{
"id": "stepfun/step-3.7-flash",
"slug": "stepfun/step-3.7-flash-20260528",
"name": "Step 3.7 Flash",
"vendor": "StepFun",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Step 3.7 Flash is StepFun's high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...",
"created": 1779985069,
"created_human": "28 mei 2026",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2,
"completion_per_1m": 1.15,
"blended_per_1m": 0.4375,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.44 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 406.2,
"ttft_seconds": 0.81
},
"benchmarks": {
"intelligence_index": 29.7,
"coding_index": 37.3,
"math_index": null,
"agentic_index": 21.5,
"mmlu_pro": null,
"gpqa": 80.9,
"hle": 19.9,
"livecodebench": null,
"scicode": 40,
"aime": null,
"ifbench": 67.3,
"tau2": 98.5,
"terminalbench": 36,
"design_arena": {
"overall_elo": 1202,
"code_elo": 1217,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1221,
"rank": 15
},
{
"category": "gamedev",
"elo": 1222,
"rank": 40
},
{
"category": "dataviz",
"elo": 1211,
"rank": 42
},
{
"category": "website",
"elo": 1224,
"rank": 43
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 42,
"coding": 47,
"writing": 42,
"agentic": 39,
"overall": 43
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 2,
"speed": 5
},
"popularity": 66,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/stepfun/step-3.7-flash",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 33
},
"curated": true,
"pop_rank": 30
},
{
"id": "anthropic/claude-haiku-4.5",
"slug": "anthropic/claude-4.5-haiku-20251001",
"name": "Claude Haiku 4.5",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...",
"created": 1760547638,
"created_human": "15 okt 2025",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1,
"completion_per_1m": 5,
"blended_per_1m": 2,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$2.0 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 29.6,
"coding_index": 43.9,
"math_index": null,
"agentic_index": 16.4,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1154,
"code_elo": 1165,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1185,
"rank": 28
},
{
"category": "svg",
"elo": 1081,
"rank": 54
},
{
"category": "dataviz",
"elo": 1167,
"rank": 60
},
{
"category": "gamedev",
"elo": 1164,
"rank": 60
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 42,
"coding": 55,
"writing": 42,
"agentic": 30,
"overall": 43
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 2,
"speed": 5
},
"popularity": 40,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-haiku-4.5",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "anthropic/claude-sonnet-4.5",
"slug": "anthropic/claude-4.5-sonnet-20250929",
"name": "Claude Sonnet 4.5",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Sonnet 4.5 is Anthropic’s advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...",
"created": 1759161676,
"created_human": "29 sep 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 3,
"completion_per_1m": 15,
"blended_per_1m": 6,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$6.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1225,
"code_elo": 1233,
"count": 11,
"top": [
{
"category": "asciiart",
"elo": 1246,
"rank": 10
},
{
"category": "fullstack",
"elo": 1121,
"rank": 18
},
{
"category": "mobileapps",
"elo": 1185,
"rank": 21
},
{
"category": "webapps",
"elo": 1130,
"rank": 21
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 50,
"coding": 52,
"writing": 50,
"agentic": 0,
"overall": 43
},
"stars": {
"intelligence": 3,
"coding": 3,
"writing": 3,
"agentic": 0,
"speed": 3
},
"popularity": 46,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-sonnet-4.5",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 14
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-v3.1-terminus",
"slug": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek V3.1 Terminus",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...",
"created": 1758548275,
"created_human": "22 sep 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 163840,
"context_human": "164K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.27,
"completion_per_1m": 0.95,
"blended_per_1m": 0.44,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.44 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 26.3,
"coding_index": null,
"math_index": 89.7,
"agentic_index": null,
"mmlu_pro": 85.1,
"gpqa": 79.2,
"hle": 15.2,
"livecodebench": 79.8,
"scicode": 40.6,
"aime": 89.7,
"ifbench": 57,
"tau2": 37.1,
"terminalbench": 30.3,
"design_arena": {
"overall_elo": 1205,
"code_elo": 1226,
"count": 7,
"top": [
{
"category": "uicomponent",
"elo": 1236,
"rank": 34
},
{
"category": "3d",
"elo": 1219,
"rank": 37
},
{
"category": "codecategories",
"elo": 1226,
"rank": 38
},
{
"category": "website",
"elo": 1230,
"rank": 41
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 38,
"coding": 50,
"writing": 38,
"agentic": 52,
"overall": 43
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 3,
"speed": 3
},
"popularity": 53,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-v3.1-terminus",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-2.5-pro",
"slug": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
"created": 1750169544,
"created_human": "17 jun 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 117.6,
"ttft_seconds": 22.77
},
"benchmarks": {
"intelligence_index": 27,
"coding_index": null,
"math_index": 87.7,
"agentic_index": null,
"mmlu_pro": 86.2,
"gpqa": 84.4,
"hle": 21.1,
"livecodebench": 80.1,
"scicode": 42.8,
"aime": 87.7,
"ifbench": 48.7,
"tau2": 54.1,
"terminalbench": 26.5,
"design_arena": {
"overall_elo": 1207,
"code_elo": 1204,
"count": 6,
"top": [
{
"category": "dataviz",
"elo": 1289,
"rank": 11
},
{
"category": "uicomponent",
"elo": 1198,
"rank": 48
},
{
"category": "website",
"elo": 1210,
"rank": 49
},
{
"category": "codecategories",
"elo": 1204,
"rank": 51
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 39,
"coding": 44,
"writing": 39,
"agentic": 62,
"overall": 43
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 3,
"speed": 4
},
"popularity": 52,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/google/gemini-2.5-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o3",
"slug": "openai/o3-2025-04-16",
"name": "o3",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....",
"created": 1744823457,
"created_human": "16 apr 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 8,
"blended_per_1m": 3.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.5 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 163.1,
"ttft_seconds": 4.87
},
"benchmarks": {
"intelligence_index": 30.4,
"coding_index": null,
"math_index": 88.3,
"agentic_index": null,
"mmlu_pro": 85.3,
"gpqa": 82.7,
"hle": 20,
"livecodebench": 80.8,
"scicode": 41,
"aime": 88.3,
"ifbench": 71.4,
"tau2": 80.7,
"terminalbench": 37.1,
"design_arena": {
"overall_elo": 1105,
"code_elo": 1070,
"count": 5,
"top": [
{
"category": "dataviz",
"elo": 1200,
"rank": 49
},
{
"category": "gamedev",
"elo": 1101,
"rank": 78
},
{
"category": "uicomponent",
"elo": 1072,
"rank": 79
},
{
"category": "codecategories",
"elo": 1070,
"rank": 85
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 43,
"coding": 6,
"writing": 43,
"agentic": 91,
"overall": 43
},
"stars": {
"intelligence": 2,
"coding": 1,
"writing": 2,
"agentic": 5,
"speed": 4
},
"popularity": 53,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/o3",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 15
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemma-4-31b-it:free",
"slug": "google/gemma-4-31b-it-20260402",
"name": "Gemma 4 31B (free)",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...",
"created": 1775148486,
"created_human": "2 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 29.4,
"coding_index": 43.4,
"math_index": null,
"agentic_index": 14.4,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 42,
"coding": 54,
"writing": 42,
"agentic": 26,
"overall": 42
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 1,
"speed": 3
},
"popularity": 33,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/google/gemma-4-31b-it:free",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 78
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemma-4-31b-it",
"slug": "google/gemma-4-31b-it-20260402",
"name": "Gemma 4 31B",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...",
"created": 1775148486,
"created_human": "2 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.12,
"completion_per_1m": 0.35,
"blended_per_1m": 0.1775,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 35.2,
"ttft_seconds": 0.96
},
"benchmarks": {
"intelligence_index": 29.4,
"coding_index": 43.4,
"math_index": null,
"agentic_index": 14.4,
"mmlu_pro": null,
"gpqa": 85.7,
"hle": 22.7,
"livecodebench": null,
"scicode": 43.4,
"aime": null,
"ifbench": 75.6,
"tau2": 59.9,
"terminalbench": 43.4,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 42,
"coding": 54,
"writing": 42,
"agentic": 26,
"overall": 42
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 1,
"speed": 2
},
"popularity": 49,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemma-4-31b-it",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 47
},
"curated": false,
"pop_rank": null
},
{
"id": "arcee-ai/trinity-large-thinking",
"slug": "arcee-ai/trinity-large-thinking",
"name": "Trinity Large Thinking",
"vendor": "Arcee AI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...",
"created": 1775058318,
"created_human": "1 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 0.8,
"blended_per_1m": 0.3875,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.39 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 257.4,
"ttft_seconds": 0.71
},
"benchmarks": {
"intelligence_index": 24.5,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 75.2,
"hle": 14.7,
"livecodebench": null,
"scicode": 36.1,
"aime": null,
"ifbench": 56.3,
"tau2": 90.1,
"terminalbench": 22.7,
"design_arena": {
"overall_elo": 1131,
"code_elo": 1166,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1086,
"rank": 43
},
{
"category": "svg",
"elo": 1071,
"rank": 57
},
{
"category": "3d",
"elo": 1160,
"rank": 59
},
{
"category": "website",
"elo": 1178,
"rank": 60
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 35,
"coding": 33,
"writing": 35,
"agentic": 87,
"overall": 42
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 4,
"speed": 5
},
"popularity": 59,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/arcee-ai/trinity-large-thinking",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": true,
"pop_rank": 40
},
{
"id": "qwen/qwen3-max-thinking",
"slug": "qwen/qwen3-max-thinking-20260123",
"name": "Qwen3 Max Thinking",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...",
"created": 1770671901,
"created_human": "9 feb 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.78,
"completion_per_1m": 3.9,
"blended_per_1m": 1.56,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.6 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 31.7,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 86.1,
"hle": 26.2,
"livecodebench": null,
"scicode": 43.1,
"aime": null,
"ifbench": 70.7,
"tau2": 83.6,
"terminalbench": 24.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 45,
"coding": 0,
"writing": 45,
"agentic": 83,
"overall": 42
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 4,
"speed": 2
},
"popularity": 46,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-max-thinking",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 21
},
"curated": false,
"pop_rank": null
},
{
"id": "anthropic/claude-opus-4.1",
"slug": "anthropic/claude-4.1-opus-20250805",
"name": "Claude Opus 4.1",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...",
"created": 1754411591,
"created_human": "5 aug 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 15,
"completion_per_1m": 75,
"blended_per_1m": 30,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$30 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1220,
"code_elo": 1221,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1215,
"rank": 17
},
{
"category": "svg",
"elo": 1208,
"rank": 23
},
{
"category": "3d",
"elo": 1230,
"rank": 35
},
{
"category": "gamedev",
"elo": 1239,
"rank": 35
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 49,
"coding": 49,
"writing": 49,
"agentic": 0,
"overall": 42
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 0,
"speed": 2
},
"popularity": 43,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4.1",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 7
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-35b-a3b",
"slug": "qwen/qwen3.5-35b-a3b-20260224",
"name": "Qwen3.5-35B-A3B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...",
"created": 1772053822,
"created_human": "25 feb 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.14,
"completion_per_1m": 1,
"blended_per_1m": 0.355,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.36 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 171.7,
"ttft_seconds": 1.06
},
"benchmarks": {
"intelligence_index": 29.3,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 84.5,
"hle": 19.7,
"livecodebench": null,
"scicode": 37.7,
"aime": null,
"ifbench": 72.5,
"tau2": 89.2,
"terminalbench": 26.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 42,
"coding": 0,
"writing": 42,
"agentic": 89,
"overall": 41
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 4,
"speed": 4
},
"popularity": 46,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-35b-a3b",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 36
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-3-pro-image-preview",
"slug": "google/gemini-3-pro-image-preview-20251120",
"name": "Nano Banana Pro (Gemini 3 Pro Image Preview)",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Nano Banana Pro is Google’s advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
"created": 1763653797,
"created_human": "20 nov 2025",
"knowledge_cutoff": null,
"context_length": 65536,
"context_human": "66K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": true,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 12,
"blended_per_1m": 4.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.5 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1271,
"code_elo": null,
"count": 4,
"top": [
{
"category": "imageediting",
"elo": 1271,
"rank": 1
},
{
"category": "graphicdesign",
"elo": 1284,
"rank": 2
},
{
"category": "image",
"elo": 1271,
"rank": 2
},
{
"category": "logo",
"elo": 1259,
"rank": 2
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 63,
"coding": 0,
"writing": 63,
"agentic": 0,
"overall": 41
},
"stars": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 0,
"speed": 2
},
"popularity": 46,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Schrijven & e-mails",
"Complexe vraagstukken",
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3-pro-image-preview",
"available": true,
"tier": {
"key": "topklasse",
"label": "Topklasse",
"sublabel": "voor de zwaarste taken",
"icon": "sparkle",
"desc": "De allerslimste, krachtigste modellen. Topkwaliteit voor de moeilijkste taken — en de hoogste prijs.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o1",
"slug": "openai/o1-2024-12-17",
"name": "o1",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...",
"created": 1734459999,
"created_human": "17 dec 2024",
"knowledge_cutoff": "2023-10-31",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 15,
"completion_per_1m": 60,
"blended_per_1m": 26.25,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$26 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 150.4,
"ttft_seconds": 12.42
},
"benchmarks": {
"intelligence_index": 23.4,
"coding_index": 39.7,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 84.1,
"gpqa": 74.7,
"hle": 7.7,
"livecodebench": 67.9,
"scicode": 35.8,
"aime": 72.3,
"ifbench": 70.3,
"tau2": 62.6,
"terminalbench": 12.9,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 33,
"coding": 50,
"writing": 33,
"agentic": 58,
"overall": 40
},
"stars": {
"intelligence": 2,
"coding": 3,
"writing": 2,
"agentic": 3,
"speed": 4
},
"popularity": 38,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/o1",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 5
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-3.1-flash-lite",
"slug": "google/gemini-3.1-flash-lite-20260507",
"name": "Gemini 3.1 Flash Lite",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...",
"created": 1778168828,
"created_human": "7 mei 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 1.5,
"blended_per_1m": 0.5625,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.56 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 350.3,
"ttft_seconds": 4.74
},
"benchmarks": {
"intelligence_index": 25,
"coding_index": 34.7,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 82.2,
"hle": 16.2,
"livecodebench": null,
"scicode": 41.9,
"aime": null,
"ifbench": 77.2,
"tau2": 31.3,
"terminalbench": 31.1,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 36,
"coding": 43,
"writing": 36,
"agentic": 48,
"overall": 39
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 2,
"speed": 5
},
"popularity": 48,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3.1-flash-lite",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": false,
"pop_rank": null
},
{
"id": "moonshotai/kimi-k2-0905",
"slug": "moonshotai/kimi-k2-0905",
"name": "Kimi K2 0905",
"vendor": "Moonshot AI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...",
"created": 1757021147,
"created_human": "4 sep 2025",
"knowledge_cutoff": "2024-12-31",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.6,
"completion_per_1m": 2.5,
"blended_per_1m": 1.075,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.1 per 1M tokens"
},
"speed": 1,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 25.6,
"ttft_seconds": 1.53
},
"benchmarks": {
"intelligence_index": 23.5,
"coding_index": null,
"math_index": 57.3,
"agentic_index": null,
"mmlu_pro": 81.9,
"gpqa": 76.7,
"hle": 6.3,
"livecodebench": 61,
"scicode": 30.7,
"aime": 57.3,
"ifbench": 41.7,
"tau2": 73.4,
"terminalbench": 23.5,
"design_arena": {
"overall_elo": 1150,
"code_elo": 1148,
"count": 2,
"top": [
{
"category": "codecategories",
"elo": 1148,
"rank": 71
},
{
"category": "website",
"elo": 1151,
"rank": 72
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 34,
"coding": 28,
"writing": 36,
"agentic": 75,
"overall": 39
},
"stars": {
"intelligence": 2,
"coding": 1,
"writing": 2,
"agentic": 4,
"speed": 1
},
"popularity": 47,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/moonshotai/kimi-k2-0905",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "inclusionai/ling-2.6-1t",
"slug": "inclusionai/ling-2.6-1t-20260423",
"name": "Ling-2.6-1T",
"vendor": "inclusionAI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...",
"created": 1776948238,
"created_human": "23 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.075,
"completion_per_1m": 0.625,
"blended_per_1m": 0.2125,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.21 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 26.1,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 75.2,
"hle": 8.2,
"livecodebench": null,
"scicode": 37,
"aime": null,
"ifbench": 56.9,
"tau2": 89.8,
"terminalbench": 31.1,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 37,
"coding": 0,
"writing": 39,
"agentic": 93,
"overall": 38
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 5,
"speed": 3
},
"popularity": 48,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Voordelig in bulk"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/inclusionai/ling-2.6-1t",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 38
},
"curated": false,
"pop_rank": null
},
{
"id": "stepfun/step-3.5-flash",
"slug": "stepfun/step-3.5-flash",
"name": "Step 3.5 Flash",
"vendor": "StepFun",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Step 3.5 Flash is StepFun's highly capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....",
"created": 1769728337,
"created_human": "29 jan 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.09,
"completion_per_1m": 0.3,
"blended_per_1m": 0.1425,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.14 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 204.8,
"ttft_seconds": 0.86
},
"benchmarks": {
"intelligence_index": 26,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 82.6,
"hle": 22.6,
"livecodebench": null,
"scicode": 38.5,
"aime": null,
"ifbench": 66.5,
"tau2": 87.4,
"terminalbench": 32.6,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 37,
"coding": 0,
"writing": 37,
"agentic": 92,
"overall": 38
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 5,
"speed": 5
},
"popularity": 42,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/stepfun/step-3.5-flash",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 45
},
"curated": false,
"pop_rank": null
},
{
"id": "anthropic/claude-opus-4",
"slug": "anthropic/claude-4-opus-20250522",
"name": "Claude Opus 4",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...",
"created": 1747931245,
"created_human": "22 mei 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 15,
"completion_per_1m": 75,
"blended_per_1m": 30,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$30 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1207,
"code_elo": 1211,
"count": 7,
"top": [
{
"category": "svg",
"elo": 1183,
"rank": 34
},
{
"category": "gamedev",
"elo": 1238,
"rank": 36
},
{
"category": "3d",
"elo": 1217,
"rank": 39
},
{
"category": "uicomponent",
"elo": 1207,
"rank": 44
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 45,
"coding": 46,
"writing": 45,
"agentic": 0,
"overall": 38
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 0,
"speed": 2
},
"popularity": 41,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-opus-4",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 6
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemma-4-26b-a4b-it:free",
"slug": "google/gemma-4-26b-a4b-it-20260403",
"name": "Gemma 4 26B A4B (free)",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...",
"created": 1775227989,
"created_human": "3 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 25.7,
"coding_index": 39.3,
"math_index": null,
"agentic_index": 11,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 37,
"coding": 49,
"writing": 37,
"agentic": 20,
"overall": 37
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 1,
"speed": 3
},
"popularity": 31,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/google/gemma-4-26b-a4b-it:free",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 69
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemma-4-26b-a4b-it",
"slug": "google/gemma-4-26b-a4b-it-20260403",
"name": "Gemma 4 26B A4B",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...",
"created": 1775227989,
"created_human": "3 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.06,
"completion_per_1m": 0.33,
"blended_per_1m": 0.1275,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.13 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 25.7,
"coding_index": 39.3,
"math_index": null,
"agentic_index": 11,
"mmlu_pro": null,
"gpqa": 79.2,
"hle": 18.3,
"livecodebench": null,
"scicode": 40,
"aime": null,
"ifbench": 72.4,
"tau2": 43.6,
"terminalbench": 39,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 37,
"coding": 49,
"writing": 37,
"agentic": 20,
"overall": 37
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 1,
"speed": 3
},
"popularity": 46,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen",
"Voordelig in bulk"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemma-4-26b-a4b-it",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 47
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-plus-02-15",
"slug": "qwen/qwen3.5-plus-20260216",
"name": "Qwen3.5 Plus 2026-02-15",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...",
"created": 1771229416,
"created_human": "16 feb 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.26,
"completion_per_1m": 1.56,
"blended_per_1m": 0.585,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.59 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1192,
"code_elo": 1217,
"count": 8,
"top": [
{
"category": "uicomponent",
"elo": 1232,
"rank": 36
},
{
"category": "svg",
"elo": 1164,
"rank": 37
},
{
"category": "asciiart",
"elo": 1139,
"rank": 39
},
{
"category": "website",
"elo": 1231,
"rank": 40
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 41,
"coding": 48,
"writing": 41,
"agentic": 0,
"overall": 36
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 0,
"speed": 3
},
"popularity": 43,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-plus-02-15",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 28
},
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-3-super-120b-a12b:free",
"slug": "nvidia/nemotron-3-super-120b-a12b-20230311",
"name": "Nemotron 3 Super (free)",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...",
"created": 1773245239,
"created_human": "11 mrt 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 25.4,
"coding_index": 37.7,
"math_index": null,
"agentic_index": 8.7,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 36,
"coding": 47,
"writing": 36,
"agentic": 16,
"overall": 35
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 1,
"speed": 3
},
"popularity": 29,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"long-context",
"free"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 67
},
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-3-super-120b-a12b",
"slug": "nvidia/nemotron-3-super-120b-a12b-20230311",
"name": "Nemotron 3 Super",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...",
"created": 1773245239,
"created_human": "11 mrt 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.09,
"completion_per_1m": 0.45,
"blended_per_1m": 0.18,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 25.4,
"coding_index": 37.7,
"math_index": null,
"agentic_index": 8.7,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 36,
"coding": 47,
"writing": 36,
"agentic": 16,
"overall": 35
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 1,
"speed": 3
},
"popularity": 29,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 40
},
"curated": false,
"pop_rank": null
},
{
"id": "inception/mercury-2",
"slug": "inception/mercury-2-20260304",
"name": "Mercury 2",
"vendor": "Inception",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...",
"created": 1772636275,
"created_human": "4 mrt 2026",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 0.75,
"blended_per_1m": 0.375,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.38 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 1204.4,
"ttft_seconds": 2.99
},
"benchmarks": {
"intelligence_index": 25.3,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 77,
"hle": 15.5,
"livecodebench": null,
"scicode": 38.7,
"aime": null,
"ifbench": 69.8,
"tau2": 70.8,
"terminalbench": 26.5,
"design_arena": {
"overall_elo": 1034,
"code_elo": null,
"count": 1,
"top": [
{
"category": "gamedev",
"elo": 1034,
"rank": 91
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 36,
"coding": 0,
"writing": 36,
"agentic": 75,
"overall": 35
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 4,
"speed": 5
},
"popularity": 52,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice",
"Voordelig in bulk"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/inception/mercury-2",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 30
},
"curated": false,
"pop_rank": null
},
{
"id": "z-ai/glm-4.5",
"slug": "z-ai/glm-4.5",
"name": "GLM 4.5",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-4.5 is our flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...",
"created": 1753471347,
"created_human": "25 jul 2025",
"knowledge_cutoff": "2024-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.6,
"completion_per_1m": 2.2,
"blended_per_1m": 1,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.0 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 55.1,
"ttft_seconds": 1.31
},
"benchmarks": {
"intelligence_index": 19.5,
"coding_index": null,
"math_index": 73.7,
"agentic_index": null,
"mmlu_pro": 83.5,
"gpqa": 78.2,
"hle": 12.2,
"livecodebench": 73.8,
"scicode": 34.8,
"aime": 73.7,
"ifbench": 44.1,
"tau2": 43,
"terminalbench": 22,
"design_arena": {
"overall_elo": 1206,
"code_elo": 1215,
"count": 7,
"top": [
{
"category": "3d",
"elo": 1249,
"rank": 30
},
{
"category": "svg",
"elo": 1152,
"rank": 39
},
{
"category": "gamedev",
"elo": 1212,
"rank": 43
},
{
"category": "codecategories",
"elo": 1215,
"rank": 47
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 28,
"coding": 47,
"writing": 28,
"agentic": 50,
"overall": 35
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 1,
"agentic": 3,
"speed": 2
},
"popularity": 48,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-4.5",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 16
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-2.5-pro-preview",
"slug": "google/gemini-2.5-pro-preview-06-05",
"name": "Gemini 2.5 Pro Preview 06-05",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
"created": 1749137257,
"created_human": "5 jun 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 117.6,
"ttft_seconds": 22.77
},
"benchmarks": {
"intelligence_index": 27,
"coding_index": null,
"math_index": 87.7,
"agentic_index": null,
"mmlu_pro": 86.2,
"gpqa": 84.4,
"hle": 21.1,
"livecodebench": 80.1,
"scicode": 42.8,
"aime": 87.7,
"ifbench": 48.7,
"tau2": 54.1,
"terminalbench": 26.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 39,
"coding": 0,
"writing": 39,
"agentic": 62,
"overall": 35
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 3,
"speed": 4
},
"popularity": 40,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/google/gemini-2.5-pro-preview",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-3.1-flash-lite-preview",
"slug": "google/gemini-3.1-flash-lite-preview-20260303",
"name": "Gemini 3.1 Flash Lite Preview",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...",
"created": 1772512673,
"created_human": "3 mrt 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 1.5,
"blended_per_1m": 0.5625,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.56 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 350.3,
"ttft_seconds": 4.74
},
"benchmarks": {
"intelligence_index": 25,
"coding_index": 34.7,
"math_index": null,
"agentic_index": 6.2,
"mmlu_pro": null,
"gpqa": 82.2,
"hle": 16.2,
"livecodebench": null,
"scicode": 41.9,
"aime": null,
"ifbench": 77.2,
"tau2": 31.3,
"terminalbench": 31.1,
"design_arena": {
"overall_elo": 1126,
"code_elo": 1122,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1212,
"rank": 18
},
{
"category": "svg",
"elo": 1108,
"rank": 48
},
{
"category": "uicomponent",
"elo": 1125,
"rank": 69
},
{
"category": "3d",
"elo": 1127,
"rank": 72
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 36,
"coding": 43,
"writing": 36,
"agentic": 11,
"overall": 34
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 1,
"speed": 5
},
"popularity": 57,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3.1-flash-lite-preview",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": true,
"pop_rank": 48
},
{
"id": "anthropic/claude-sonnet-4",
"slug": "anthropic/claude-4-sonnet-20250522",
"name": "Claude Sonnet 4",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%)…",
"created": 1747930371,
"created_human": "22 mei 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 3,
"completion_per_1m": 15,
"blended_per_1m": 6,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$6.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1188,
"code_elo": 1192,
"count": 7,
"top": [
{
"category": "3d",
"elo": 1218,
"rank": 38
},
{
"category": "svg",
"elo": 1134,
"rank": 43
},
{
"category": "gamedev",
"elo": 1206,
"rank": 45
},
{
"category": "dataviz",
"elo": 1195,
"rank": 50
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 39,
"coding": 41,
"writing": 39,
"agentic": 0,
"overall": 34
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 0,
"speed": 3
},
"popularity": 38,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-sonnet-4",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 11
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-chat-v3.1",
"slug": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek V3.1",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...",
"created": 1755779628,
"created_human": "21 aug 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 163840,
"context_human": "164K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.21,
"completion_per_1m": 0.79,
"blended_per_1m": 0.355,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.36 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 21,
"coding_index": null,
"math_index": 49.7,
"agentic_index": null,
"mmlu_pro": 83.3,
"gpqa": 73.5,
"hle": 6.3,
"livecodebench": 57.7,
"scicode": 36.7,
"aime": 49.7,
"ifbench": 37.8,
"tau2": 34.8,
"terminalbench": 24.2,
"design_arena": {
"overall_elo": 1134,
"code_elo": 1162,
"count": 7,
"top": [
{
"category": "3d",
"elo": 1156,
"rank": 61
},
{
"category": "website",
"elo": 1166,
"rank": 63
},
{
"category": "gamedev",
"elo": 1152,
"rank": 64
},
{
"category": "uicomponent",
"elo": 1138,
"rank": 64
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 30,
"coding": 32,
"writing": 30,
"agentic": 45,
"overall": 33
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 2,
"speed": 3
},
"popularity": 49,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-chat-v3.1",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-oss-120b:free",
"slug": "openai/gpt-oss-120b",
"name": "gpt-oss-120b (free)",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optim…",
"created": 1754414231,
"created_human": "5 aug 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 23.8,
"coding_index": 30.4,
"math_index": null,
"agentic_index": 13.2,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1014,
"code_elo": 1013,
"count": 6,
"top": [
{
"category": "gamedev",
"elo": 1060,
"rank": 84
},
{
"category": "dataviz",
"elo": 1043,
"rank": 86
},
{
"category": "3d",
"elo": 979,
"rank": 89
},
{
"category": "uicomponent",
"elo": 978,
"rank": 90
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 34,
"coding": 38,
"writing": 34,
"agentic": 24,
"overall": 33
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 1,
"speed": 3
},
"popularity": 35,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-oss-120b:free",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 63
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-oss-120b",
"slug": "openai/gpt-oss-120b",
"name": "gpt-oss-120b",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optim…",
"created": 1754414231,
"created_human": "5 aug 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.039,
"completion_per_1m": 0.18,
"blended_per_1m": 0.0743,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.07 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 346.5,
"ttft_seconds": 0.55
},
"benchmarks": {
"intelligence_index": 23.8,
"coding_index": 30.4,
"math_index": 93.4,
"agentic_index": 13.2,
"mmlu_pro": 80.8,
"gpqa": 78.2,
"hle": 18.5,
"livecodebench": 87.8,
"scicode": 38.9,
"aime": 93.4,
"ifbench": 69,
"tau2": 65.8,
"terminalbench": 26.2,
"design_arena": {
"overall_elo": 1014,
"code_elo": 1013,
"count": 6,
"top": [
{
"category": "gamedev",
"elo": 1060,
"rank": 84
},
{
"category": "dataviz",
"elo": 1043,
"rank": 86
},
{
"category": "3d",
"elo": 979,
"rank": 89
},
{
"category": "uicomponent",
"elo": 978,
"rank": 90
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 34,
"coding": 38,
"writing": 34,
"agentic": 24,
"overall": 33
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 1,
"speed": 5
},
"popularity": 50,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-oss-120b",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 54
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-coder",
"slug": "qwen/qwen3-coder-480b-a35b-07-25",
"name": "Qwen3 Coder 480B A35B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...",
"created": 1753230546,
"created_human": "23 jul 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.22,
"completion_per_1m": 1.8,
"blended_per_1m": 0.615,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.62 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 64.9,
"ttft_seconds": 1.7
},
"benchmarks": {
"intelligence_index": 18,
"coding_index": null,
"math_index": 39.3,
"agentic_index": null,
"mmlu_pro": 78.8,
"gpqa": 61.8,
"hle": 4.4,
"livecodebench": 58.5,
"scicode": 35.9,
"aime": 39.3,
"ifbench": 40.5,
"tau2": 43.6,
"terminalbench": 18.9,
"design_arena": {
"overall_elo": 1171,
"code_elo": 1193,
"count": 5,
"top": [
{
"category": "codecategories",
"elo": 1193,
"rank": 54
},
{
"category": "uicomponent",
"elo": 1169,
"rank": 55
},
{
"category": "website",
"elo": 1202,
"rank": 55
},
{
"category": "gamedev",
"elo": 1168,
"rank": 58
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 26,
"coding": 41,
"writing": 27,
"agentic": 48,
"overall": 33
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 1,
"agentic": 2,
"speed": 3
},
"popularity": 46,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten"
],
"categories": [
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-coder",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o4-mini-high",
"slug": "openai/o4-mini-high-2025-04-16",
"name": "o4 Mini High",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...",
"created": 1744824212,
"created_human": "16 apr 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.1,
"completion_per_1m": 4.4,
"blended_per_1m": 1.925,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.9 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 172.1,
"ttft_seconds": 19.61
},
"benchmarks": {
"intelligence_index": 25.6,
"coding_index": null,
"math_index": 90.7,
"agentic_index": null,
"mmlu_pro": 83.2,
"gpqa": 78.4,
"hle": 17.5,
"livecodebench": 85.9,
"scicode": 46.5,
"aime": 90.7,
"ifbench": 68.7,
"tau2": 55.6,
"terminalbench": 15.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 37,
"coding": 0,
"writing": 37,
"agentic": 54,
"overall": 32
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 3,
"speed": 4
},
"popularity": 39,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/o4-mini-high",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 16
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o4-mini",
"slug": "openai/o4-mini-2025-04-16",
"name": "o4 Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...",
"created": 1744820942,
"created_human": "16 apr 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.1,
"completion_per_1m": 4.4,
"blended_per_1m": 1.925,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.9 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 172.1,
"ttft_seconds": 19.61
},
"benchmarks": {
"intelligence_index": 25.6,
"coding_index": null,
"math_index": 90.7,
"agentic_index": null,
"mmlu_pro": 83.2,
"gpqa": 78.4,
"hle": 17.5,
"livecodebench": 85.9,
"scicode": 46.5,
"aime": 90.7,
"ifbench": 68.7,
"tau2": 55.6,
"terminalbench": 15.2,
"design_arena": {
"overall_elo": 1021,
"code_elo": 1026,
"count": 6,
"top": [
{
"category": "gamedev",
"elo": 1070,
"rank": 82
},
{
"category": "uicomponent",
"elo": 1038,
"rank": 83
},
{
"category": "dataviz",
"elo": 1034,
"rank": 87
},
{
"category": "3d",
"elo": 931,
"rank": 93
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 37,
"coding": 0,
"writing": 37,
"agentic": 54,
"overall": 32
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 3,
"speed": 4
},
"popularity": 51,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/o4-mini",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 16
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o3-mini-high",
"slug": "openai/o3-mini-high-2025-01-31",
"name": "o3 Mini High",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...",
"created": 1739372611,
"created_human": "12 feb 2025",
"knowledge_cutoff": "2023-10-31",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.1,
"completion_per_1m": 4.4,
"blended_per_1m": 1.925,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.9 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 221.3,
"ttft_seconds": 4.87
},
"benchmarks": {
"intelligence_index": 19,
"coding_index": 42.1,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 79.1,
"gpqa": 74.8,
"hle": 8.7,
"livecodebench": 71.7,
"scicode": 39.9,
"aime": 77,
"ifbench": null,
"tau2": 28.7,
"terminalbench": 6.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 27,
"coding": 53,
"writing": 27,
"agentic": 27,
"overall": 32
},
"stars": {
"intelligence": 1,
"coding": 3,
"writing": 1,
"agentic": 1,
"speed": 5
},
"popularity": 35,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/o3-mini-high",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 12
},
"curated": false,
"pop_rank": null
},
{
"id": "inclusionai/ling-2.6-flash",
"slug": "inclusionai/ling-2.6-flash-20260421",
"name": "Ling-2.6-flash",
"vendor": "inclusionAI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....",
"created": 1776795886,
"created_human": "21 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.01,
"completion_per_1m": 0.03,
"blended_per_1m": 0.015,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.02 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 19.3,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 59.3,
"hle": 6.2,
"livecodebench": null,
"scicode": 27.1,
"aime": null,
"ifbench": 57.4,
"tau2": 86,
"terminalbench": 21.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 28,
"coding": 0,
"writing": 29,
"agentic": 82,
"overall": 31
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 4,
"speed": 5
},
"popularity": 44,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Chat & klantenservice"
],
"categories": [
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/inclusionai/ling-2.6-flash",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 52
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-coder-next",
"slug": "qwen/qwen3-coder-next-2025-02-03",
"name": "Qwen3 Coder Next",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...",
"created": 1770164101,
"created_human": "4 feb 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.11,
"completion_per_1m": 0.8,
"blended_per_1m": 0.2825,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.28 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 109.4,
"ttft_seconds": 1.15
},
"benchmarks": {
"intelligence_index": 21.2,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 73.7,
"hle": 9.3,
"livecodebench": null,
"scicode": 32.3,
"aime": null,
"ifbench": 35.2,
"tau2": 79.5,
"terminalbench": 18.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 30,
"coding": 0,
"writing": 32,
"agentic": 75,
"overall": 31
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 4,
"speed": 3
},
"popularity": 39,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-coder-next",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 28
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5-image-mini",
"slug": "openai/gpt-5-image-mini",
"name": "GPT-5 Image Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...",
"created": 1760624583,
"created_human": "16 okt 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": true,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2.5,
"completion_per_1m": 2,
"blended_per_1m": 2.375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$2.4 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1214,
"code_elo": null,
"count": 3,
"top": [
{
"category": "logo",
"elo": 1228,
"rank": 3
},
{
"category": "graphicdesign",
"elo": 1202,
"rank": 6
},
{
"category": "image",
"elo": 1211,
"rank": 6
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 47,
"coding": 0,
"writing": 47,
"agentic": 0,
"overall": 31
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 0,
"speed": 5
},
"popularity": 38,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5-image-mini",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5-image",
"slug": "openai/gpt-5-image",
"name": "GPT-5 Image",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...",
"created": 1760447986,
"created_human": "14 okt 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": true,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 10,
"completion_per_1m": 10,
"blended_per_1m": 10,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$10 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1217,
"code_elo": null,
"count": 3,
"top": [
{
"category": "graphicdesign",
"elo": 1210,
"rank": 4
},
{
"category": "image",
"elo": 1219,
"rank": 4
},
{
"category": "logo",
"elo": 1222,
"rank": 4
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 48,
"coding": 0,
"writing": 48,
"agentic": 0,
"overall": 31
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 0,
"speed": 3
},
"popularity": 39,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5-image",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 11
},
"curated": false,
"pop_rank": null
},
{
"id": "z-ai/glm-4.5-air",
"slug": "z-ai/glm-4.5-air",
"name": "GLM 4.5 Air",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-4.5-Air is the lightweight variant of our flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...",
"created": 1753471258,
"created_human": "25 jul 2025",
"knowledge_cutoff": "2024-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.13,
"completion_per_1m": 0.85,
"blended_per_1m": 0.31,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.31 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 84.1,
"ttft_seconds": 1.61
},
"benchmarks": {
"intelligence_index": 16.5,
"coding_index": null,
"math_index": 80.7,
"agentic_index": null,
"mmlu_pro": 81.5,
"gpqa": 73.3,
"hle": 6.8,
"livecodebench": 68.4,
"scicode": 30.6,
"aime": 80.7,
"ifbench": 37.6,
"tau2": 46.5,
"terminalbench": 20.5,
"design_arena": {
"overall_elo": 1183,
"code_elo": 1188,
"count": 7,
"top": [
{
"category": "dataviz",
"elo": 1236,
"rank": 33
},
{
"category": "3d",
"elo": 1201,
"rank": 44
},
{
"category": "svg",
"elo": 1127,
"rank": 45
},
{
"category": "uicomponent",
"elo": 1178,
"rank": 54
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 24,
"coding": 39,
"writing": 24,
"agentic": 52,
"overall": 31
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 1,
"agentic": 3,
"speed": 3
},
"popularity": 46,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-4.5-air",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 21
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-coder:free",
"slug": "qwen/qwen3-coder-480b-a35b-07-25",
"name": "Qwen3 Coder 480B A35B (free)",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...",
"created": 1753230546,
"created_human": "23 jul 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1171,
"code_elo": 1193,
"count": 5,
"top": [
{
"category": "codecategories",
"elo": 1193,
"rank": 54
},
{
"category": "uicomponent",
"elo": 1169,
"rank": 55
},
{
"category": "website",
"elo": 1202,
"rank": 55
},
{
"category": "gamedev",
"elo": 1168,
"rank": 58
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 35,
"coding": 41,
"writing": 37,
"agentic": 0,
"overall": 31
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 0,
"speed": 3
},
"popularity": 34,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Voordelig in bulk"
],
"categories": [
"long-context",
"free"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-coder:free",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 65
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-235b-a22b-2507",
"slug": "qwen/qwen3-235b-a22b-07-25",
"name": "Qwen3 235B A22B Instruct 2507",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, …",
"created": 1753119555,
"created_human": "21 jul 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.09,
"completion_per_1m": 0.1,
"blended_per_1m": 0.0925,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.09 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 76.2,
"ttft_seconds": 1.16
},
"benchmarks": {
"intelligence_index": 22.3,
"coding_index": null,
"math_index": 91,
"agentic_index": null,
"mmlu_pro": 84.3,
"gpqa": 79,
"hle": 15,
"livecodebench": 78.8,
"scicode": 42.4,
"aime": 91,
"ifbench": 51.2,
"tau2": 53.2,
"terminalbench": 13.6,
"design_arena": {
"overall_elo": 1067,
"code_elo": 1089,
"count": 6,
"top": [
{
"category": "dataviz",
"elo": 1101,
"rank": 77
},
{
"category": "3d",
"elo": 1073,
"rank": 80
},
{
"category": "codecategories",
"elo": 1089,
"rank": 81
},
{
"category": "website",
"elo": 1101,
"rank": 83
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 32,
"coding": 11,
"writing": 34,
"agentic": 51,
"overall": 31
},
"stars": {
"intelligence": 2,
"coding": 1,
"writing": 2,
"agentic": 3,
"speed": 3
},
"popularity": 49,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 46
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-r1-0528",
"slug": "deepseek/deepseek-r1-0528",
"name": "R1 0528",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...",
"created": 1748455170,
"created_human": "28 mei 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 163840,
"context_human": "164K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.5,
"completion_per_1m": 2.15,
"blended_per_1m": 0.9125,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.91 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1173,
"code_elo": 1189,
"count": 7,
"top": [
{
"category": "dataviz",
"elo": 1221,
"rank": 36
},
{
"category": "3d",
"elo": 1190,
"rank": 49
},
{
"category": "svg",
"elo": 1094,
"rank": 49
},
{
"category": "uicomponent",
"elo": 1159,
"rank": 56
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 35,
"coding": 40,
"writing": 35,
"agentic": 0,
"overall": 31
},
"stars": {
"intelligence": 2,
"coding": 2,
"writing": 2,
"agentic": 0,
"speed": 2
},
"popularity": 36,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-r1-0528",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 20
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"slug": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen3 235B A22B Thinking 2507",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...",
"created": 1753449557,
"created_human": "25 jul 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.1,
"blended_per_1m": 0.1,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.10 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 76.2,
"ttft_seconds": 1.16
},
"benchmarks": {
"intelligence_index": 22.3,
"coding_index": null,
"math_index": 91,
"agentic_index": null,
"mmlu_pro": 84.3,
"gpqa": 79,
"hle": 15,
"livecodebench": 78.8,
"scicode": 42.4,
"aime": 91,
"ifbench": 51.2,
"tau2": 53.2,
"terminalbench": 13.6,
"design_arena": {
"overall_elo": 1045,
"code_elo": 1083,
"count": 6,
"top": [
{
"category": "3d",
"elo": 1078,
"rank": 79
},
{
"category": "codecategories",
"elo": 1083,
"rank": 83
},
{
"category": "website",
"elo": 1096,
"rank": 84
},
{
"category": "dataviz",
"elo": 990,
"rank": 89
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 32,
"coding": 9,
"writing": 32,
"agentic": 51,
"overall": 30
},
"stars": {
"intelligence": 2,
"coding": 1,
"writing": 2,
"agentic": 3,
"speed": 3
},
"popularity": 49,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 45
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-2.5-flash",
"slug": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with g…",
"created": 1750172488,
"created_human": "17 jun 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 2.5,
"blended_per_1m": 0.85,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.85 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 190.7,
"ttft_seconds": 10.98
},
"benchmarks": {
"intelligence_index": 20.1,
"coding_index": null,
"math_index": 73.3,
"agentic_index": null,
"mmlu_pro": 83.2,
"gpqa": 79,
"hle": 11.1,
"livecodebench": 69.5,
"scicode": 39.4,
"aime": 73.3,
"ifbench": 50.3,
"tau2": 31.6,
"terminalbench": 13.6,
"design_arena": {
"overall_elo": 1141,
"code_elo": 1154,
"count": 7,
"top": [
{
"category": "svg",
"elo": 1076,
"rank": 56
},
{
"category": "dataviz",
"elo": 1170,
"rank": 59
},
{
"category": "uicomponent",
"elo": 1147,
"rank": 63
},
{
"category": "3d",
"elo": 1150,
"rank": 64
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 29,
"coding": 30,
"writing": 29,
"agentic": 35,
"overall": 30
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 1,
"agentic": 2,
"speed": 4
},
"popularity": 49,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemini-2.5-flash",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o3-pro",
"slug": "openai/o3-pro-2025-06-10",
"name": "o3 Pro",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...",
"created": 1749598352,
"created_human": "10 jun 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 20,
"completion_per_1m": 80,
"blended_per_1m": 35,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$35 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 34.6,
"ttft_seconds": 59.26
},
"benchmarks": {
"intelligence_index": 32.5,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 84.5,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 46,
"coding": 0,
"writing": 46,
"agentic": 0,
"overall": 30
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 0,
"speed": 2
},
"popularity": 43,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/o3-pro",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 6
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5-nano",
"slug": "openai/gpt-5-nano-2025-08-07",
"name": "GPT-5 Nano",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...",
"created": 1754587402,
"created_human": "7 aug 2025",
"knowledge_cutoff": "2024-05-31",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.05,
"completion_per_1m": 0.4,
"blended_per_1m": 0.1375,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.14 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 150.2,
"ttft_seconds": 74.4
},
"benchmarks": {
"intelligence_index": 19.9,
"coding_index": null,
"math_index": 83.7,
"agentic_index": null,
"mmlu_pro": 78,
"gpqa": 67.6,
"hle": 8.2,
"livecodebench": 78.9,
"scicode": 36.6,
"aime": 83.7,
"ifbench": 67.6,
"tau2": 36.5,
"terminalbench": 12.1,
"design_arena": {
"overall_elo": 1110,
"code_elo": 1135,
"count": 6,
"top": [
{
"category": "uicomponent",
"elo": 1121,
"rank": 70
},
{
"category": "codecategories",
"elo": 1135,
"rank": 74
},
{
"category": "website",
"elo": 1145,
"rank": 74
},
{
"category": "dataviz",
"elo": 1103,
"rank": 76
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 28,
"coding": 24,
"writing": 28,
"agentic": 37,
"overall": 29
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 2,
"speed": 4
},
"popularity": 47,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5-nano",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 35
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-2.5-flash-image",
"slug": "google/gemini-2.5-flash-image",
"name": "Nano Banana (Gemini 2.5 Flash Image)",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...",
"created": 1759870431,
"created_human": "7 okt 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 32768,
"context_human": "33K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": true,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 2.5,
"blended_per_1m": 0.85,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.85 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1201,
"code_elo": null,
"count": 3,
"top": [
{
"category": "graphicdesign",
"elo": 1202,
"rank": 5
},
{
"category": "image",
"elo": 1214,
"rank": 5
},
{
"category": "logo",
"elo": 1188,
"rank": 6
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 43,
"coding": 0,
"writing": 45,
"agentic": 0,
"overall": 28
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 0,
"speed": 5
},
"popularity": 36,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemini-2.5-flash-image",
"available": true,
"tier": {
"key": "professioneel",
"label": "Professioneel",
"sublabel": "meest gekozen",
"icon": "check",
"desc": "Sterke allrounders met de beste balans tussen kwaliteit en prijs. Voor de meeste organisaties de slimste keuze.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 26
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-large-2512",
"slug": "mistralai/mistral-large-2512",
"name": "Mistral Large 3 2512",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral Large 3 2512 is Mistral’s highly capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.",
"created": 1764624472,
"created_human": "1 dec 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.5,
"completion_per_1m": 1.5,
"blended_per_1m": 0.75,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.75 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1152,
"code_elo": 1192,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1114,
"rank": 42
},
{
"category": "3d",
"elo": 1178,
"rank": 51
},
{
"category": "website",
"elo": 1205,
"rank": 53
},
{
"category": "dataviz",
"elo": 1179,
"rank": 55
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 29,
"coding": 41,
"writing": 30,
"agentic": 0,
"overall": 27
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 2,
"agentic": 0,
"speed": 3
},
"popularity": 34,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-large-2512",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"slug": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen3 VL 235B A22B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/ta…",
"created": 1758668687,
"created_human": "23 sep 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2,
"completion_per_1m": 0.88,
"blended_per_1m": 0.37,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.37 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 57.2,
"ttft_seconds": 1.16
},
"benchmarks": {
"intelligence_index": 20.6,
"coding_index": null,
"math_index": 88.3,
"agentic_index": null,
"mmlu_pro": 83.6,
"gpqa": 77.2,
"hle": 10.1,
"livecodebench": 64.6,
"scicode": 39.9,
"aime": 88.3,
"ifbench": 56.5,
"tau2": 54.1,
"terminalbench": 11.4,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 29,
"coding": 0,
"writing": 30,
"agentic": 50,
"overall": 27
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 2,
"agentic": 3,
"speed": 2
},
"popularity": 36,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-instruct",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 24
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-medium-3.1",
"slug": "mistralai/mistral-medium-3.1",
"name": "Mistral Medium 3.1",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...",
"created": 1755095639,
"created_human": "13 aug 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.4,
"completion_per_1m": 2,
"blended_per_1m": 0.8,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.80 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 90.7,
"ttft_seconds": 0.58
},
"benchmarks": {
"intelligence_index": 14.8,
"coding_index": null,
"math_index": 38.3,
"agentic_index": null,
"mmlu_pro": 68.3,
"gpqa": 58.8,
"hle": 4.4,
"livecodebench": 40.6,
"scicode": 33.8,
"aime": 38.3,
"ifbench": 39.8,
"tau2": 40.6,
"terminalbench": 10.6,
"design_arena": {
"overall_elo": 1136,
"code_elo": 1171,
"count": 8,
"top": [
{
"category": "asciiart",
"elo": 1043,
"rank": 45
},
{
"category": "dataviz",
"elo": 1191,
"rank": 52
},
{
"category": "3d",
"elo": 1161,
"rank": 58
},
{
"category": "codecategories",
"elo": 1171,
"rank": 60
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 21,
"coding": 35,
"writing": 22,
"agentic": 39,
"overall": 27
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 1,
"agentic": 2,
"speed": 3
},
"popularity": 46,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-medium-3.1",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4.1",
"slug": "openai/gpt-4.1-2025-04-14",
"name": "GPT-4.1",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...",
"created": 1744651385,
"created_human": "14 apr 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 1047576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 8,
"blended_per_1m": 3.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.5 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 139.8,
"ttft_seconds": 0.6
},
"benchmarks": {
"intelligence_index": 19.4,
"coding_index": null,
"math_index": 34.7,
"agentic_index": null,
"mmlu_pro": 80.6,
"gpqa": 66.6,
"hle": 4.6,
"livecodebench": 45.7,
"scicode": 38.1,
"aime": 34.7,
"ifbench": 43,
"tau2": 47.1,
"terminalbench": 13.6,
"design_arena": {
"overall_elo": 1073,
"code_elo": 1076,
"count": 6,
"top": [
{
"category": "dataviz",
"elo": 1147,
"rank": 64
},
{
"category": "gamedev",
"elo": 1147,
"rank": 65
},
{
"category": "uicomponent",
"elo": 1055,
"rank": 80
},
{
"category": "codecategories",
"elo": 1076,
"rank": 84
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 28,
"coding": 7,
"writing": 29,
"agentic": 47,
"overall": 27
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 2,
"speed": 4
},
"popularity": 47,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4.1",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 9
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-small-2603",
"slug": "mistralai/mistral-small-2603",
"name": "Mistral Small 4",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...",
"created": 1773695685,
"created_human": "16 mrt 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 0.6,
"blended_per_1m": 0.2625,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.26 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 176.5,
"ttft_seconds": 0.59
},
"benchmarks": {
"intelligence_index": 20.8,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 76.9,
"hle": 9.5,
"livecodebench": null,
"scicode": 38,
"aime": null,
"ifbench": 48.2,
"tau2": 41.2,
"terminalbench": 17.4,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 30,
"coding": 0,
"writing": 30,
"agentic": 45,
"overall": 26
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 2,
"speed": 4
},
"popularity": 42,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-small-2603",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-vl-235b-a22b-thinking",
"slug": "qwen/qwen3-vl-235b-a22b-thinking",
"name": "Qwen3 VL 235B A22B Thinking",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....",
"created": 1758668690,
"created_human": "23 sep 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.26,
"completion_per_1m": 2.6,
"blended_per_1m": 0.845,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.85 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 57.2,
"ttft_seconds": 1.16
},
"benchmarks": {
"intelligence_index": 20.6,
"coding_index": null,
"math_index": 88.3,
"agentic_index": null,
"mmlu_pro": 83.6,
"gpqa": 77.2,
"hle": 10.1,
"livecodebench": 64.6,
"scicode": 39.9,
"aime": 88.3,
"ifbench": 56.5,
"tau2": 54.1,
"terminalbench": 11.4,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 29,
"coding": 0,
"writing": 29,
"agentic": 50,
"overall": 26
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 3,
"speed": 2
},
"popularity": 36,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-thinking",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-r1",
"slug": "deepseek/deepseek-r1",
"name": "R1",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....",
"created": 1737381095,
"created_human": "20 jan 2025",
"knowledge_cutoff": "2024-07-31",
"context_length": 163840,
"context_human": "164K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.7,
"completion_per_1m": 2.5,
"blended_per_1m": 1.15,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.2 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 20.1,
"coding_index": null,
"math_index": 76,
"agentic_index": null,
"mmlu_pro": 84.9,
"gpqa": 81.3,
"hle": 14.9,
"livecodebench": 77,
"scicode": 40.3,
"aime": 76,
"ifbench": 39.6,
"tau2": 36.5,
"terminalbench": 15.9,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 29,
"coding": 0,
"writing": 29,
"agentic": 40,
"overall": 25
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 2
},
"popularity": 36,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-r1",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 15
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-2.5-flash-lite-preview-09-2025",
"slug": "google/gemini-2.5-flash-lite-preview-09-2025",
"name": "Gemini 2.5 Flash Lite Preview 09-2025",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...",
"created": 1758819686,
"created_human": "25 sep 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.4,
"blended_per_1m": 0.175,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 15.1,
"coding_index": null,
"math_index": 68.7,
"agentic_index": null,
"mmlu_pro": 80.8,
"gpqa": 70.9,
"hle": 6.6,
"livecodebench": 68.8,
"scicode": 28.7,
"aime": 68.7,
"ifbench": 52.6,
"tau2": 30.7,
"terminalbench": 12.9,
"design_arena": {
"overall_elo": 1107,
"code_elo": 1131,
"count": 6,
"top": [
{
"category": "dataviz",
"elo": 1133,
"rank": 71
},
{
"category": "codecategories",
"elo": 1131,
"rank": 75
},
{
"category": "gamedev",
"elo": 1114,
"rank": 75
},
{
"category": "website",
"elo": 1143,
"rank": 75
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 22,
"coding": 23,
"writing": 22,
"agentic": 34,
"overall": 24
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 2,
"speed": 5
},
"popularity": 45,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemini-2.5-flash-lite-preview-09-2025",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-next-80b-a3b-thinking",
"slug": "qwen/qwen3-next-80b-a3b-thinking-2509",
"name": "Qwen3 Next 80B A3B Thinking",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agenti…",
"created": 1757612284,
"created_human": "11 sep 2025",
"knowledge_cutoff": "2025-09-30",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.0975,
"completion_per_1m": 0.78,
"blended_per_1m": 0.2681,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.27 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 189.3,
"ttft_seconds": 1.09
},
"benchmarks": {
"intelligence_index": 19.8,
"coding_index": null,
"math_index": 84.3,
"agentic_index": null,
"mmlu_pro": 82.4,
"gpqa": 75.9,
"hle": 11.7,
"livecodebench": 78.4,
"scicode": 38.8,
"aime": 84.3,
"ifbench": 60.7,
"tau2": 41.5,
"terminalbench": 9.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 28,
"coding": 0,
"writing": 28,
"agentic": 39,
"overall": 24
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 4
},
"popularity": 35,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-thinking",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 26
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"slug": "qwen/qwen3-next-80b-a3b-instruct-2509",
"name": "Qwen3 Next 80B A3B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multili…",
"created": 1757612213,
"created_human": "11 sep 2025",
"knowledge_cutoff": "2025-09-30",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.09,
"completion_per_1m": 1.1,
"blended_per_1m": 0.3425,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.34 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 189.3,
"ttft_seconds": 1.09
},
"benchmarks": {
"intelligence_index": 19.8,
"coding_index": null,
"math_index": 84.3,
"agentic_index": null,
"mmlu_pro": 82.4,
"gpqa": 75.9,
"hle": 11.7,
"livecodebench": 78.4,
"scicode": 38.8,
"aime": 84.3,
"ifbench": 60.7,
"tau2": 41.5,
"terminalbench": 9.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 28,
"coding": 0,
"writing": 29,
"agentic": 39,
"overall": 24
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 4
},
"popularity": 35,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 24
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-vl-32b-instruct",
"slug": "qwen/qwen3-vl-32b-instruct",
"name": "Qwen3 VL 32B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced …",
"created": 1761231332,
"created_human": "23 okt 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.104,
"completion_per_1m": 0.416,
"blended_per_1m": 0.182,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 96.1,
"ttft_seconds": 1.37
},
"benchmarks": {
"intelligence_index": 17.9,
"coding_index": null,
"math_index": 84.7,
"agentic_index": null,
"mmlu_pro": 81.8,
"gpqa": 73.3,
"hle": 9.6,
"livecodebench": 73.8,
"scicode": 28.5,
"aime": 84.7,
"ifbench": 59.4,
"tau2": 45.6,
"terminalbench": 7.6,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 26,
"coding": 0,
"writing": 27,
"agentic": 41,
"overall": 23
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 3
},
"popularity": 34,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-vl-32b-instruct",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 29
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4.1-mini",
"slug": "openai/gpt-4.1-mini-2025-04-14",
"name": "GPT-4.1 Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...",
"created": 1744651381,
"created_human": "14 apr 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 1047576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.4,
"completion_per_1m": 1.6,
"blended_per_1m": 0.7,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.70 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 92.1,
"ttft_seconds": 0.56
},
"benchmarks": {
"intelligence_index": 16.3,
"coding_index": null,
"math_index": 46.3,
"agentic_index": null,
"mmlu_pro": 78.1,
"gpqa": 66.4,
"hle": 4.6,
"livecodebench": 48.3,
"scicode": 40.4,
"aime": 46.3,
"ifbench": 38.3,
"tau2": 52.9,
"terminalbench": 7.6,
"design_arena": {
"overall_elo": 1038,
"code_elo": 1044,
"count": 6,
"top": [
{
"category": "gamedev",
"elo": 1138,
"rank": 70
},
{
"category": "dataviz",
"elo": 1076,
"rank": 79
},
{
"category": "uicomponent",
"elo": 1016,
"rank": 86
},
{
"category": "codecategories",
"elo": 1044,
"rank": 92
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 23,
"coding": 0,
"writing": 24,
"agentic": 47,
"overall": 22
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 3
},
"popularity": 45,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Zelfstandige taken",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4.1-mini",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 15
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-chat-v3-0324",
"slug": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek V3 0324",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...",
"created": 1742824755,
"created_human": "24 mrt 2025",
"knowledge_cutoff": "2024-07-31",
"context_length": 163840,
"context_human": "164K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2,
"completion_per_1m": 0.77,
"blended_per_1m": 0.3425,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.34 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 15.7,
"coding_index": null,
"math_index": 41,
"agentic_index": null,
"mmlu_pro": 81.9,
"gpqa": 65.5,
"hle": 5.2,
"livecodebench": 40.5,
"scicode": 35.8,
"aime": 41,
"ifbench": 41,
"tau2": 47.1,
"terminalbench": 15.2,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 22,
"coding": 0,
"writing": 23,
"agentic": 48,
"overall": 22
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 3
},
"popularity": 33,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-chat-v3-0324",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o3-mini",
"slug": "openai/o3-mini-2025-01-31",
"name": "o3 Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...",
"created": 1738351721,
"created_human": "31 jan 2025",
"knowledge_cutoff": "2023-10-31",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.1,
"completion_per_1m": 4.4,
"blended_per_1m": 1.925,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.9 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 221.3,
"ttft_seconds": 4.87
},
"benchmarks": {
"intelligence_index": 19,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 79.1,
"gpqa": 74.8,
"hle": 8.7,
"livecodebench": 71.7,
"scicode": 39.9,
"aime": 77,
"ifbench": null,
"tau2": 28.7,
"terminalbench": 6.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 27,
"coding": 0,
"writing": 27,
"agentic": 27,
"overall": 22
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 5
},
"popularity": 35,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/o3-mini",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 12
},
"curated": false,
"pop_rank": null
},
{
"id": "z-ai/glm-4.6v",
"slug": "z-ai/glm-4.6-20251208",
"name": "GLM 4.6V",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...",
"created": 1765207462,
"created_human": "8 dec 2025",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 0.9,
"blended_per_1m": 0.45,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.45 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 59.1,
"ttft_seconds": 1.1
},
"benchmarks": {
"intelligence_index": 16.8,
"coding_index": null,
"math_index": 85.3,
"agentic_index": null,
"mmlu_pro": 79.9,
"gpqa": 71.9,
"hle": 8.9,
"livecodebench": 16,
"scicode": 30.4,
"aime": 85.3,
"ifbench": 30.1,
"tau2": 31.6,
"terminalbench": 14.4,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 24,
"coding": 0,
"writing": 24,
"agentic": 35,
"overall": 21
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 2
},
"popularity": 33,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-4.6v",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-2.5-pro-preview-05-06",
"slug": "google/gemini-2.5-pro-preview-03-25",
"name": "Gemini 2.5 Pro Preview 05-06",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
"created": 1746578513,
"created_human": "7 mei 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 22.3,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 83.7,
"gpqa": 82.2,
"hle": 15.4,
"livecodebench": 77,
"scicode": 41.6,
"aime": 84.3,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 32,
"coding": 0,
"writing": 32,
"agentic": 0,
"overall": 21
},
"stars": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 0,
"speed": 2
},
"popularity": 37,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 11
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-oss-20b:free",
"slug": "openai/gpt-oss-20b",
"name": "gpt-oss-20b (free)",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...",
"created": 1754414229,
"created_human": "5 aug 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 14.9,
"coding_index": 20.7,
"math_index": null,
"agentic_index": 3.1,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 937,
"code_elo": null,
"count": 2,
"top": [
{
"category": "dataviz",
"elo": 977,
"rank": 91
},
{
"category": "website",
"elo": 896,
"rank": 106
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 21,
"coding": 26,
"writing": 21,
"agentic": 6,
"overall": 20
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 26,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-oss-20b:free",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 39
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-oss-20b",
"slug": "openai/gpt-oss-20b",
"name": "gpt-oss-20b",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...",
"created": 1754414229,
"created_human": "5 aug 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.029,
"completion_per_1m": 0.14,
"blended_per_1m": 0.0568,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.06 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 228.1,
"ttft_seconds": 0.64
},
"benchmarks": {
"intelligence_index": 14.9,
"coding_index": 20.7,
"math_index": 89.3,
"agentic_index": 3.1,
"mmlu_pro": 74.8,
"gpqa": 68.8,
"hle": 9.8,
"livecodebench": 77.7,
"scicode": 34.4,
"aime": 89.3,
"ifbench": 65.1,
"tau2": 60.2,
"terminalbench": 13.9,
"design_arena": {
"overall_elo": 937,
"code_elo": null,
"count": 2,
"top": [
{
"category": "dataviz",
"elo": 977,
"rank": 91
},
{
"category": "website",
"elo": 896,
"rank": 106
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 21,
"coding": 26,
"writing": 21,
"agentic": 6,
"overall": 20
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 5
},
"popularity": 41,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-oss-20b",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 37
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-chat",
"slug": "deepseek/deepseek-chat-v3",
"name": "DeepSeek V3",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek-V3 is the model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...",
"created": 1735241320,
"created_human": "26 dec 2024",
"knowledge_cutoff": "2024-07-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2002,
"completion_per_1m": 0.8001,
"blended_per_1m": 0.3502,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.35 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 10.4,
"coding_index": null,
"math_index": 26,
"agentic_index": null,
"mmlu_pro": 75.2,
"gpqa": 55.7,
"hle": 3.6,
"livecodebench": 35.9,
"scicode": 35.4,
"aime": 26,
"ifbench": 34.8,
"tau2": 22.8,
"terminalbench": 6.8,
"design_arena": {
"overall_elo": 1133,
"code_elo": 1159,
"count": 7,
"top": [
{
"category": "3d",
"elo": 1166,
"rank": 54
},
{
"category": "uicomponent",
"elo": 1148,
"rank": 62
},
{
"category": "svg",
"elo": 1032,
"rank": 65
},
{
"category": "website",
"elo": 1163,
"rank": 65
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 15,
"coding": 31,
"writing": 16,
"agentic": 23,
"overall": 20
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 42,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-chat",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"slug": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen3 30B A3B Thinking 2507",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces…",
"created": 1756399192,
"created_human": "28 aug 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.08,
"completion_per_1m": 0.4,
"blended_per_1m": 0.16,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.16 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 155.3,
"ttft_seconds": 1.15
},
"benchmarks": {
"intelligence_index": 15.8,
"coding_index": null,
"math_index": 56.3,
"agentic_index": null,
"mmlu_pro": 80.5,
"gpqa": 70.7,
"hle": 9.8,
"livecodebench": 70.7,
"scicode": 33.3,
"aime": 56.3,
"ifbench": 50.7,
"tau2": 28.1,
"terminalbench": 5.3,
"design_arena": {
"overall_elo": 971,
"code_elo": null,
"count": 2,
"top": [
{
"category": "dataviz",
"elo": 968,
"rank": 93
},
{
"category": "website",
"elo": 974,
"rank": 101
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 23,
"coding": 0,
"writing": 23,
"agentic": 26,
"overall": 19
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 42,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-30b-a3b-thinking-2507",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 27
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"slug": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen3 30B A3B Instruct 2507",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingua…",
"created": 1753806965,
"created_human": "29 jul 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.0482,
"completion_per_1m": 0.1931,
"blended_per_1m": 0.0844,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.08 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 155.3,
"ttft_seconds": 1.15
},
"benchmarks": {
"intelligence_index": 15.8,
"coding_index": null,
"math_index": 56.3,
"agentic_index": null,
"mmlu_pro": 80.5,
"gpqa": 70.7,
"hle": 9.8,
"livecodebench": 70.7,
"scicode": 33.3,
"aime": 56.3,
"ifbench": 50.7,
"tau2": 28.1,
"terminalbench": 5.3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 23,
"coding": 0,
"writing": 24,
"agentic": 26,
"overall": 19
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 33,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "beste-koop",
"label": "Beste koop",
"tone": "good",
"icon": "sparkle",
"desc": "Veel kwaliteit voor weinig geld — voor de meeste mensen de slimste keuze.",
"score": 35
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-medium-3",
"slug": "mistralai/mistral-medium-3",
"name": "Mistral Medium 3",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× l…",
"created": 1746627341,
"created_human": "7 mei 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.4,
"completion_per_1m": 2,
"blended_per_1m": 0.8,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.80 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 46.2,
"ttft_seconds": 0.58
},
"benchmarks": {
"intelligence_index": 12.5,
"coding_index": null,
"math_index": 30.3,
"agentic_index": null,
"mmlu_pro": 76,
"gpqa": 57.8,
"hle": 4.3,
"livecodebench": 40,
"scicode": 33.1,
"aime": 30.3,
"ifbench": 39.3,
"tau2": 24.3,
"terminalbench": 3.8,
"design_arena": {
"overall_elo": 1107,
"code_elo": 1119,
"count": 6,
"top": [
{
"category": "3d",
"elo": 1161,
"rank": 57
},
{
"category": "uicomponent",
"elo": 1081,
"rank": 76
},
{
"category": "codecategories",
"elo": 1119,
"rank": 77
},
{
"category": "website",
"elo": 1122,
"rank": 80
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 18,
"coding": 20,
"writing": 19,
"agentic": 22,
"overall": 19
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 2
},
"popularity": 43,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-medium-3",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 11
},
"curated": false,
"pop_rank": null
},
{
"id": "upstage/solar-pro-3",
"slug": "upstage/solar-pro-3",
"name": "Solar Pro 3",
"vendor": "Upstage",
"origin": {
"country": "Zuid-Korea",
"country_code": "KR",
"flag": "🇰🇷",
"region": "asia",
"region_label": "Azië (overig)",
"eu": false
},
"description": "Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...",
"created": 1769481200,
"created_human": "27 jan 2026",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 0.6,
"blended_per_1m": 0.2625,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.26 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 14.1,
"coding_index": 16.2,
"math_index": null,
"agentic_index": 2.7,
"mmlu_pro": null,
"gpqa": 72.4,
"hle": 10.1,
"livecodebench": null,
"scicode": 24.7,
"aime": null,
"ifbench": 71.2,
"tau2": 86.3,
"terminalbench": 12,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 20,
"coding": 20,
"writing": 20,
"agentic": 5,
"overall": 18
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 2
},
"popularity": 34,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/upstage/solar-pro-3",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"slug": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen3 Coder 30B A3B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...",
"created": 1753972379,
"created_human": "31 jul 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 160000,
"context_human": "160K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.07,
"completion_per_1m": 0.27,
"blended_per_1m": 0.12,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.12 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 111.6,
"ttft_seconds": 1.47
},
"benchmarks": {
"intelligence_index": 13.6,
"coding_index": null,
"math_index": 29,
"agentic_index": null,
"mmlu_pro": 70.6,
"gpqa": 51.6,
"hle": 4,
"livecodebench": 40.3,
"scicode": 27.8,
"aime": 29,
"ifbench": 32.7,
"tau2": 34.5,
"terminalbench": 15.2,
"design_arena": {
"overall_elo": 1120,
"code_elo": null,
"count": 3,
"top": [
{
"category": "uicomponent",
"elo": 1101,
"rank": 72
},
{
"category": "dataviz",
"elo": 1127,
"rank": 73
},
{
"category": "website",
"elo": 1131,
"rank": 76
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 19,
"coding": 0,
"writing": 20,
"agentic": 38,
"overall": 18
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 4
},
"popularity": 41,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 25
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-4-maverick",
"slug": "meta-llama/llama-4-maverick-17b-128e-instruct",
"name": "Llama 4 Maverick",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...",
"created": 1743881822,
"created_human": "5 apr 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 0.6,
"blended_per_1m": 0.2625,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.26 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 121.6,
"ttft_seconds": 0.64
},
"benchmarks": {
"intelligence_index": 14.3,
"coding_index": 16.3,
"math_index": 19.3,
"agentic_index": 1.3,
"mmlu_pro": 80.9,
"gpqa": 67.1,
"hle": 4.8,
"livecodebench": 39.7,
"scicode": 33.1,
"aime": 19.3,
"ifbench": 43,
"tau2": 17.8,
"terminalbench": 7.9,
"design_arena": {
"overall_elo": 934,
"code_elo": 930,
"count": 6,
"top": [
{
"category": "3d",
"elo": 978,
"rank": 90
},
{
"category": "uicomponent",
"elo": 954,
"rank": 93
},
{
"category": "dataviz",
"elo": 925,
"rank": 99
},
{
"category": "codecategories",
"elo": 930,
"rank": 101
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 20,
"coding": 20,
"writing": 21,
"agentic": 2,
"overall": 18
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 44,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-4-maverick",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/o1-pro",
"slug": "openai/o1-pro",
"name": "o1-pro",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...",
"created": 1742423211,
"created_human": "19 mrt 2025",
"knowledge_cutoff": "2023-10-31",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 150,
"completion_per_1m": 600,
"blended_per_1m": 262.5,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$263 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 18.9,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 27,
"coding": 0,
"writing": 27,
"agentic": 0,
"overall": 18
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 2
},
"popularity": 35,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/o1-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 2
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-235b-a22b",
"slug": "qwen/qwen3-235b-a22b-04-28",
"name": "Qwen3 235B A22B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...",
"created": 1745875757,
"created_human": "28 apr 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.455,
"completion_per_1m": 1.82,
"blended_per_1m": 0.7963,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.80 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 61.2,
"ttft_seconds": 1.33
},
"benchmarks": {
"intelligence_index": 13.4,
"coding_index": null,
"math_index": 82,
"agentic_index": null,
"mmlu_pro": 82.8,
"gpqa": 70,
"hle": 11.7,
"livecodebench": 62.2,
"scicode": 39.9,
"aime": 82,
"ifbench": 38.7,
"tau2": 24,
"terminalbench": 6.1,
"design_arena": {
"overall_elo": 1020,
"code_elo": 1053,
"count": 6,
"top": [
{
"category": "dataviz",
"elo": 1044,
"rank": 85
},
{
"category": "uicomponent",
"elo": 1016,
"rank": 87
},
{
"category": "website",
"elo": 1074,
"rank": 88
},
{
"category": "codecategories",
"elo": 1053,
"rank": 90
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 19,
"coding": 1,
"writing": 19,
"agentic": 23,
"overall": 16
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 43,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-235b-a22b",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 12
},
"curated": false,
"pop_rank": null
},
{
"id": "perplexity/sonar-reasoning-pro",
"slug": "perplexity/sonar-reasoning-pro",
"name": "Sonar Reasoning Pro",
"vendor": "Perplexity",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...",
"created": 1741313308,
"created_human": "7 mrt 2025",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 8,
"blended_per_1m": 3.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.5 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 17.8,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": 79,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 25,
"coding": 0,
"writing": 25,
"agentic": 0,
"overall": 16
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 2
},
"popularity": 34,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/perplexity/sonar-reasoning-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 8
},
"curated": false,
"pop_rank": null
},
{
"id": "perplexity/sonar-pro",
"slug": "perplexity/sonar-pro",
"name": "Sonar Pro",
"vendor": "Perplexity",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Note: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...",
"created": 1741312423,
"created_human": "7 mrt 2025",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 3,
"completion_per_1m": 15,
"blended_per_1m": 6,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$6.0 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 17.8,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": 79,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 25,
"coding": 0,
"writing": 26,
"agentic": 0,
"overall": 16
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 2
},
"popularity": 34,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/perplexity/sonar-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 7
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-vl-30b-a3b-thinking",
"slug": "qwen/qwen3-vl-30b-a3b-thinking",
"name": "Qwen3 VL 30B A3B Thinking",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...",
"created": 1759794479,
"created_human": "6 okt 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.13,
"completion_per_1m": 1.56,
"blended_per_1m": 0.4875,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.49 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 123.5,
"ttft_seconds": 1
},
"benchmarks": {
"intelligence_index": 13.3,
"coding_index": null,
"math_index": 82.3,
"agentic_index": null,
"mmlu_pro": 80.7,
"gpqa": 72,
"hle": 8.7,
"livecodebench": 69.7,
"scicode": 28.8,
"aime": 82.3,
"ifbench": 45.1,
"tau2": 19.9,
"terminalbench": 5.3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 19,
"coding": 0,
"writing": 19,
"agentic": 19,
"overall": 15
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 31,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-thinking",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 14
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"slug": "qwen/qwen3-vl-30b-a3b-instruct",
"name": "Qwen3 VL 30B A3B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in percepti…",
"created": 1759794476,
"created_human": "6 okt 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.13,
"completion_per_1m": 0.52,
"blended_per_1m": 0.2275,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.23 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 123.5,
"ttft_seconds": 1
},
"benchmarks": {
"intelligence_index": 13.3,
"coding_index": null,
"math_index": 82.3,
"agentic_index": null,
"mmlu_pro": 80.7,
"gpqa": 72,
"hle": 8.7,
"livecodebench": 69.7,
"scicode": 28.8,
"aime": 82.3,
"ifbench": 45.1,
"tau2": 19.9,
"terminalbench": 5.3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 19,
"coding": 0,
"writing": 20,
"agentic": 19,
"overall": 15
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 31,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-instruct",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4o",
"slug": "openai/gpt-4o",
"name": "GPT-4o",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...",
"created": 1715558400,
"created_human": "13 mei 2024",
"knowledge_cutoff": "2023-10-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2.5,
"completion_per_1m": 10,
"blended_per_1m": 4.375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.4 per 1M tokens"
},
"speed": 5,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 220.5,
"ttft_seconds": 0.45
},
"benchmarks": {
"intelligence_index": 11.2,
"coding_index": null,
"math_index": 6,
"agentic_index": null,
"mmlu_pro": 74.8,
"gpqa": 54.3,
"hle": 3.3,
"livecodebench": 30.9,
"scicode": 33.3,
"aime": 6,
"ifbench": 34.3,
"tau2": 25.1,
"terminalbench": 8.3,
"design_arena": {
"overall_elo": 924,
"code_elo": 911,
"count": 6,
"top": [
{
"category": "3d",
"elo": 947,
"rank": 91
},
{
"category": "uicomponent",
"elo": 940,
"rank": 95
},
{
"category": "gamedev",
"elo": 973,
"rank": 98
},
{
"category": "dataviz",
"elo": 900,
"rank": 100
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 16,
"coding": 0,
"writing": 17,
"agentic": 26,
"overall": 15
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 5
},
"popularity": 42,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4o",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 5
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/ministral-14b-2512",
"slug": "mistralai/ministral-14b-2512",
"name": "Ministral 3 14B 2512",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...",
"created": 1764681735,
"created_human": "2 dec 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2,
"completion_per_1m": 0.2,
"blended_per_1m": 0.2,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.20 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": 14.6,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1104,
"code_elo": 1115,
"count": 4,
"top": [
{
"category": "gamedev",
"elo": 1105,
"rank": 77
},
{
"category": "codecategories",
"elo": 1115,
"rank": 78
},
{
"category": "website",
"elo": 1125,
"rank": 79
},
{
"category": "3d",
"elo": 1069,
"rank": 81
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 15,
"coding": 18,
"writing": 16,
"agentic": 0,
"overall": 14
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 5
},
"popularity": 25,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/ministral-14b-2512",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 16
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-32b",
"slug": "qwen/qwen3-32b-04-28",
"name": "Qwen3 32B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...",
"created": 1745875945,
"created_human": "28 apr 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.08,
"completion_per_1m": 0.28,
"blended_per_1m": 0.13,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.13 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 95.8,
"ttft_seconds": 1.03
},
"benchmarks": {
"intelligence_index": 10.5,
"coding_index": null,
"math_index": 73,
"agentic_index": null,
"mmlu_pro": 79.8,
"gpqa": 66.8,
"hle": 8.3,
"livecodebench": 54.6,
"scicode": 35.4,
"aime": 73,
"ifbench": 36.3,
"tau2": 29.8,
"terminalbench": 3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 15,
"coding": 0,
"writing": 15,
"agentic": 25,
"overall": 14
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-32b",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "goede-waarde",
"label": "Goede prijs-kwaliteit",
"tone": "good",
"icon": "check",
"desc": "Sterke balans tussen prijs en kwaliteit.",
"score": 19
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-large-2407",
"slug": "mistralai/mistral-large-2407",
"name": "Mistral Large 2407",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....",
"created": 1731978415,
"created_human": "19 nov 2024",
"knowledge_cutoff": "2024-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 6,
"blended_per_1m": 3,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 7.3,
"coding_index": null,
"math_index": 0,
"agentic_index": null,
"mmlu_pro": 68.3,
"gpqa": 47.2,
"hle": 3.2,
"livecodebench": 26.7,
"scicode": 27.1,
"aime": 0,
"ifbench": 31.6,
"tau2": 33,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 0,
"writing": 11,
"agentic": 51,
"overall": 14
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 3,
"speed": 3
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Zelfstandige taken"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-large-2407",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 4
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen-2.5-72b-instruct",
"slug": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen2.5 72B is the series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...",
"created": 1726704000,
"created_human": "19 sep 2024",
"knowledge_cutoff": "2024-06-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.36,
"completion_per_1m": 0.4,
"blended_per_1m": 0.37,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.37 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 9.6,
"coding_index": null,
"math_index": 14,
"agentic_index": null,
"mmlu_pro": 72,
"gpqa": 49.1,
"hle": 4.2,
"livecodebench": 27.6,
"scicode": 26.7,
"aime": 14,
"ifbench": 36.9,
"tau2": 34.5,
"terminalbench": 4.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 14,
"coding": 0,
"writing": 15,
"agentic": 30,
"overall": 14
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 3
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 12
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4o-2024-08-06",
"slug": "openai/gpt-4o-2024-08-06",
"name": "GPT-4o (2024-08-06)",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more here. GPT-4o (\"o\" for \"omni\") is...",
"created": 1722902400,
"created_human": "6 aug 2024",
"knowledge_cutoff": "2023-10-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2.5,
"completion_per_1m": 10,
"blended_per_1m": 4.375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.4 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 101.7,
"ttft_seconds": 0.58
},
"benchmarks": {
"intelligence_index": 9.6,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 52.1,
"hle": 2.9,
"livecodebench": 31.7,
"scicode": 33.1,
"aime": 11.7,
"ifbench": 36,
"tau2": 28.9,
"terminalbench": 8.3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 14,
"coding": 0,
"writing": 15,
"agentic": 29,
"overall": 14
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4o-2024-08-06",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 4
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4o-2024-05-13",
"slug": "openai/gpt-4o-2024-05-13",
"name": "GPT-4o (2024-05-13)",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...",
"created": 1715558400,
"created_human": "13 mei 2024",
"knowledge_cutoff": "2023-10-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 15,
"blended_per_1m": 7.5,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$7.5 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 104.8,
"ttft_seconds": 0.57
},
"benchmarks": {
"intelligence_index": 8.6,
"coding_index": 24.2,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 74,
"gpqa": 52.6,
"hle": 2.8,
"livecodebench": 33.4,
"scicode": 30.9,
"aime": 11,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 12,
"coding": 30,
"writing": 13,
"agentic": 0,
"overall": 14
},
"stars": {
"intelligence": 1,
"coding": 2,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 28,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4o-2024-05-13",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 3
},
"curated": false,
"pop_rank": null
},
{
"id": "ibm-granite/granite-4.1-8b",
"slug": "ibm-granite/granite-4.1-8b-20260429",
"name": "Granite 4.1 8B",
"vendor": "IBM",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...",
"created": 1777577071,
"created_human": "30 apr 2026",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.05,
"completion_per_1m": 0.1,
"blended_per_1m": 0.0625,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.06 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 131.6,
"ttft_seconds": 0.45
},
"benchmarks": {
"intelligence_index": 6.7,
"coding_index": 9.5,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 43.3,
"hle": 3.8,
"livecodebench": null,
"scicode": 21.8,
"aime": null,
"ifbench": 38.6,
"tau2": 27.8,
"terminalbench": 3.4,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 12,
"writing": 11,
"agentic": 24,
"overall": 13
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 36,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/ibm-granite/granite-4.1-8b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-vl-8b-thinking",
"slug": "qwen/qwen3-vl-8b-thinking",
"name": "Qwen3 VL 8B Thinking",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal a…",
"created": 1760463746,
"created_human": "14 okt 2025",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.117,
"completion_per_1m": 1.365,
"blended_per_1m": 0.429,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.43 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 136.8,
"ttft_seconds": 1.17
},
"benchmarks": {
"intelligence_index": 10.6,
"coding_index": null,
"math_index": 30.7,
"agentic_index": null,
"mmlu_pro": 74.9,
"gpqa": 57.9,
"hle": 3.3,
"livecodebench": 35.3,
"scicode": 21.9,
"aime": 30.7,
"ifbench": 39.9,
"tau2": 22.5,
"terminalbench": 3.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 15,
"coding": 0,
"writing": 15,
"agentic": 20,
"overall": 13
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-vl-8b-thinking",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 12
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-vl-8b-instruct",
"slug": "qwen/qwen3-vl-8b-instruct",
"name": "Qwen3 VL 8B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for lo…",
"created": 1760463308,
"created_human": "14 okt 2025",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.08,
"completion_per_1m": 0.5,
"blended_per_1m": 0.185,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.19 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 136.8,
"ttft_seconds": 1.17
},
"benchmarks": {
"intelligence_index": 10.6,
"coding_index": null,
"math_index": 30.7,
"agentic_index": null,
"mmlu_pro": 74.9,
"gpqa": 57.9,
"hle": 3.3,
"livecodebench": 35.3,
"scicode": 21.9,
"aime": 30.7,
"ifbench": 39.9,
"tau2": 22.5,
"terminalbench": 3.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 15,
"coding": 0,
"writing": 16,
"agentic": 20,
"overall": 13
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-vl-8b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 16
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-2.5-flash-lite",
"slug": "google/gemini-2.5-flash-lite",
"name": "Gemini 2.5 Flash Lite",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...",
"created": 1753200276,
"created_human": "22 jul 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.4,
"blended_per_1m": 0.175,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 189.7,
"ttft_seconds": 13.35
},
"benchmarks": {
"intelligence_index": 11.4,
"coding_index": null,
"math_index": 53.3,
"agentic_index": null,
"mmlu_pro": 75.9,
"gpqa": 62.5,
"hle": 6.4,
"livecodebench": 59.3,
"scicode": 19.3,
"aime": 53.3,
"ifbench": 49.9,
"tau2": 18.4,
"terminalbench": 4.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 16,
"coding": 0,
"writing": 16,
"agentic": 18,
"overall": 13
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 30,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemini-2.5-flash-lite",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-14b",
"slug": "qwen/qwen3-14b-04-28",
"name": "Qwen3 14B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...",
"created": 1745876478,
"created_human": "28 apr 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131702,
"context_human": "132K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.24,
"blended_per_1m": 0.135,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.14 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 63.7,
"ttft_seconds": 1.02
},
"benchmarks": {
"intelligence_index": 10.1,
"coding_index": null,
"math_index": 55.7,
"agentic_index": null,
"mmlu_pro": 77.4,
"gpqa": 60.4,
"hle": 4.3,
"livecodebench": 52.3,
"scicode": 31.6,
"aime": 55.7,
"ifbench": 40.5,
"tau2": 34.5,
"terminalbench": 3.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 14,
"coding": 0,
"writing": 14,
"agentic": 29,
"overall": 13
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-14b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4-turbo",
"slug": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.",
"created": 1712620800,
"created_human": "9 apr 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 10,
"completion_per_1m": 30,
"blended_per_1m": 15,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$15 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 38.1,
"ttft_seconds": 1.28
},
"benchmarks": {
"intelligence_index": 7.9,
"coding_index": 21.5,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 69.4,
"gpqa": null,
"hle": 3.3,
"livecodebench": 29.1,
"scicode": 31.9,
"aime": 15,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 11,
"coding": 27,
"writing": 12,
"agentic": 0,
"overall": 13
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 2
},
"popularity": 28,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4-turbo",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 2
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4-turbo-preview",
"slug": "openai/gpt-4-turbo-preview",
"name": "GPT-4 Turbo Preview",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...",
"created": 1706140800,
"created_human": "25 jan 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 10,
"completion_per_1m": 30,
"blended_per_1m": 15,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$15 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 38.1,
"ttft_seconds": 1.28
},
"benchmarks": {
"intelligence_index": 7.9,
"coding_index": 21.5,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 69.4,
"gpqa": null,
"hle": 3.3,
"livecodebench": 29.1,
"scicode": 31.9,
"aime": 15,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 11,
"coding": 27,
"writing": 12,
"agentic": 0,
"overall": 13
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 2
},
"popularity": 28,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/openai/gpt-4-turbo-preview",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 2
},
"curated": false,
"pop_rank": null
},
{
"id": "z-ai/glm-4.5v",
"slug": "z-ai/glm-4.5v",
"name": "GLM 4.5V",
"vendor": "Z.ai",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understan…",
"created": 1754922288,
"created_human": "11 aug 2025",
"knowledge_cutoff": "2024-12-31",
"context_length": 65536,
"context_human": "66K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.6,
"completion_per_1m": 1.8,
"blended_per_1m": 0.9,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.90 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 45.5,
"ttft_seconds": 1.34
},
"benchmarks": {
"intelligence_index": 9.1,
"coding_index": null,
"math_index": 73,
"agentic_index": null,
"mmlu_pro": 78.8,
"gpqa": 68.4,
"hle": 5.9,
"livecodebench": 60.4,
"scicode": 22.1,
"aime": 73,
"ifbench": 34.2,
"tau2": 22.5,
"terminalbench": 5.3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 13,
"coding": 0,
"writing": 13,
"agentic": 21,
"overall": 12
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 2
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/z-ai/glm-4.5v",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 8
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-30b-a3b",
"slug": "qwen/qwen3-30b-a3b-04-28",
"name": "Qwen3 30B A3B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3, the generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...",
"created": 1745878604,
"created_human": "28 apr 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.12,
"completion_per_1m": 0.5,
"blended_per_1m": 0.215,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.22 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 112.5,
"ttft_seconds": 1.11
},
"benchmarks": {
"intelligence_index": 9.3,
"coding_index": null,
"math_index": 72.3,
"agentic_index": null,
"mmlu_pro": 77.7,
"gpqa": 61.6,
"hle": 6.6,
"livecodebench": 50.6,
"scicode": 28.5,
"aime": 72.3,
"ifbench": 41.5,
"tau2": 26,
"terminalbench": 2.3,
"design_arena": {
"overall_elo": 993,
"code_elo": 992,
"count": 5,
"top": [
{
"category": "dataviz",
"elo": 1010,
"rank": 88
},
{
"category": "uicomponent",
"elo": 1000,
"rank": 88
},
{
"category": "codecategories",
"elo": 992,
"rank": 97
},
{
"category": "gamedev",
"elo": 965,
"rank": 99
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 13,
"coding": 0,
"writing": 13,
"agentic": 22,
"overall": 12
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 40,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-30b-a3b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-4-scout",
"slug": "meta-llama/llama-4-scout-17b-16e-instruct",
"name": "Llama 4 Scout",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...",
"created": 1743881519,
"created_human": "5 apr 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 10000000,
"context_human": "10M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.3,
"blended_per_1m": 0.15,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.15 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 107.9,
"ttft_seconds": 0.59
},
"benchmarks": {
"intelligence_index": 10,
"coding_index": 8.2,
"math_index": 14,
"agentic_index": 1.1,
"mmlu_pro": 75.2,
"gpqa": 58.7,
"hle": 4.3,
"livecodebench": 29.9,
"scicode": 17,
"aime": 14,
"ifbench": 39.5,
"tau2": 15.5,
"terminalbench": 3.7,
"design_arena": {
"overall_elo": 847,
"code_elo": 840,
"count": 5,
"top": [
{
"category": "dataviz",
"elo": 939,
"rank": 95
},
{
"category": "uicomponent",
"elo": 823,
"rank": 99
},
{
"category": "codecategories",
"elo": 840,
"rank": 105
},
{
"category": "gamedev",
"elo": 840,
"rank": 105
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 14,
"coding": 10,
"writing": 15,
"agentic": 2,
"overall": 12
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 40,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-4-scout",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": false,
"pop_rank": null
},
{
"id": "deepseek/deepseek-r1-distill-llama-70b",
"slug": "deepseek/deepseek-r1-distill-llama-70b",
"name": "R1 Distill Llama 70B",
"vendor": "DeepSeek",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across...",
"created": 1737663169,
"created_human": "23 jan 2025",
"knowledge_cutoff": "2024-07-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.8,
"completion_per_1m": 0.8,
"blended_per_1m": 0.8,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.80 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 48.2,
"ttft_seconds": 0.45
},
"benchmarks": {
"intelligence_index": 9.9,
"coding_index": null,
"math_index": 53.7,
"agentic_index": null,
"mmlu_pro": 79.5,
"gpqa": 40.2,
"hle": 6.1,
"livecodebench": 26.6,
"scicode": 31.3,
"aime": 53.7,
"ifbench": 27.6,
"tau2": 21.9,
"terminalbench": 1.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 14,
"coding": 0,
"writing": 14,
"agentic": 18,
"overall": 12
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 2
},
"popularity": 29,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 9
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/ministral-8b-2512",
"slug": "mistralai/ministral-8b-2512",
"name": "Ministral 3 8B 2512",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.",
"created": 1764681654,
"created_human": "2 dec 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 0.15,
"blended_per_1m": 0.15,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.15 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": 11.4,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1095,
"code_elo": 1103,
"count": 4,
"top": [
{
"category": "3d",
"elo": 1110,
"rank": 75
},
{
"category": "codecategories",
"elo": 1103,
"rank": 80
},
{
"category": "website",
"elo": 1108,
"rank": 81
},
{
"category": "gamedev",
"elo": 1058,
"rank": 85
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 13,
"coding": 14,
"writing": 14,
"agentic": 0,
"overall": 11
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 5
},
"popularity": 24,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/ministral-8b-2512",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 16
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-8b",
"slug": "qwen/qwen3-8b-04-28",
"name": "Qwen3 8B",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...",
"created": 1745876632,
"created_human": "28 apr 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.05,
"completion_per_1m": 0.4,
"blended_per_1m": 0.1375,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.14 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 60.5,
"ttft_seconds": 1.43
},
"benchmarks": {
"intelligence_index": 7.4,
"coding_index": null,
"math_index": 19,
"agentic_index": null,
"mmlu_pro": 74.3,
"gpqa": 58.9,
"hle": 4.2,
"livecodebench": 40.6,
"scicode": 22.6,
"aime": 19,
"ifbench": 33.5,
"tau2": 27.8,
"terminalbench": 2.3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 11,
"coding": 0,
"writing": 11,
"agentic": 23,
"overall": 11
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 28,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-8b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 14
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-small-24b-instruct-2501",
"slug": "mistralai/mistral-small-24b-instruct-2501",
"name": "Mistral Small 3",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...",
"created": 1738255409,
"created_human": "30 jan 2025",
"knowledge_cutoff": "2023-10-31",
"context_length": 32768,
"context_human": "33K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.05,
"completion_per_1m": 0.08,
"blended_per_1m": 0.0575,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.06 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 159.9,
"ttft_seconds": 0.57
},
"benchmarks": {
"intelligence_index": 6.9,
"coding_index": null,
"math_index": 4.3,
"agentic_index": null,
"mmlu_pro": 65.2,
"gpqa": 46.2,
"hle": 4.1,
"livecodebench": 25.2,
"scicode": 23.6,
"aime": 4.3,
"ifbench": 26.4,
"tau2": 19.6,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 0,
"writing": 11,
"agentic": 30,
"overall": 11
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 4
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 18
},
"curated": false,
"pop_rank": null
},
{
"id": "perplexity/sonar",
"slug": "perplexity/sonar",
"name": "Sonar",
"vendor": "Perplexity",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...",
"created": 1738013808,
"created_human": "27 jan 2025",
"knowledge_cutoff": null,
"context_length": 127072,
"context_human": "127K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1,
"completion_per_1m": 1,
"blended_per_1m": 1,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 11.7,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 62.3,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": 77,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 17,
"coding": 0,
"writing": 18,
"agentic": 0,
"overall": 11
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 30,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/perplexity/sonar",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 9
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-3.3-70b-instruct",
"slug": "meta-llama/llama-3.3-70b-instruct",
"name": "Llama 3.3 70B Instruct",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...",
"created": 1733506137,
"created_human": "6 dec 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.32,
"blended_per_1m": 0.155,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.16 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 93.7,
"ttft_seconds": 0.62
},
"benchmarks": {
"intelligence_index": 8.6,
"coding_index": null,
"math_index": 7.7,
"agentic_index": null,
"mmlu_pro": 71.3,
"gpqa": 49.8,
"hle": 4,
"livecodebench": 28.8,
"scicode": 26,
"aime": 7.7,
"ifbench": 47.1,
"tau2": 26.6,
"terminalbench": 3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 12,
"coding": 0,
"writing": 13,
"agentic": 23,
"overall": 11
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 28,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 14
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4",
"slug": "openai/gpt-4",
"name": "GPT-4",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...",
"created": 1685232000,
"created_human": "28 mei 2023",
"knowledge_cutoff": "2021-09-30",
"context_length": 8191,
"context_human": "8K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 30,
"completion_per_1m": 60,
"blended_per_1m": 37.5,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$38 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 41.2,
"ttft_seconds": 0.95
},
"benchmarks": {
"intelligence_index": 7,
"coding_index": 13.1,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 16,
"writing": 11,
"agentic": 0,
"overall": 10
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 2
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/openai/gpt-4",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 1
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4.1-nano",
"slug": "openai/gpt-4.1-nano-2025-04-14",
"name": "GPT-4.1 Nano",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...",
"created": 1744651369,
"created_human": "14 apr 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 1047576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.4,
"blended_per_1m": 0.175,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 175.9,
"ttft_seconds": 0.49
},
"benchmarks": {
"intelligence_index": 7.3,
"coding_index": null,
"math_index": 24,
"agentic_index": null,
"mmlu_pro": 65.7,
"gpqa": 51.2,
"hle": 3.9,
"livecodebench": 32.6,
"scicode": 25.9,
"aime": 24,
"ifbench": 32,
"tau2": 17.3,
"terminalbench": 3.8,
"design_arena": {
"overall_elo": 996,
"code_elo": 1013,
"count": 6,
"top": [
{
"category": "3d",
"elo": 1003,
"rank": 88
},
{
"category": "gamedev",
"elo": 1038,
"rank": 89
},
{
"category": "uicomponent",
"elo": 971,
"rank": 91
},
{
"category": "codecategories",
"elo": 1013,
"rank": 95
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 0,
"writing": 11,
"agentic": 16,
"overall": 9
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 39,
"data_sources": [
"openrouter",
"artificial_analysis",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4.1-nano",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 11
},
"curated": false,
"pop_rank": null
},
{
"id": "cohere/command-a",
"slug": "cohere/command-a-03-2025",
"name": "Command A",
"vendor": "Cohere",
"origin": {
"country": "Canada",
"country_code": "CA",
"flag": "🇨🇦",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...",
"created": 1741894342,
"created_human": "13 mrt 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2.5,
"completion_per_1m": 10,
"blended_per_1m": 4.375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.4 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 74,
"ttft_seconds": 0.3
},
"benchmarks": {
"intelligence_index": 7.7,
"coding_index": null,
"math_index": 13,
"agentic_index": null,
"mmlu_pro": 71.2,
"gpqa": 52.7,
"hle": 4.6,
"livecodebench": 28.7,
"scicode": 28.1,
"aime": 13,
"ifbench": 36.5,
"tau2": 15.2,
"terminalbench": 0.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 11,
"coding": 0,
"writing": 12,
"agentic": 12,
"overall": 9
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 28,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/cohere/command-a",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 3
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-3.2-3b-instruct",
"slug": "meta-llama/llama-3.2-3b-instruct",
"name": "Llama 3.2 3B Instruct",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the transformer architecture, it...",
"created": 1727222400,
"created_human": "25 sep 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.0509,
"completion_per_1m": 0.335,
"blended_per_1m": 0.1219,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.12 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 51.8,
"ttft_seconds": 0.59
},
"benchmarks": {
"intelligence_index": 4.2,
"coding_index": null,
"math_index": 3.3,
"agentic_index": null,
"mmlu_pro": 34.7,
"gpqa": 25.5,
"hle": 5.2,
"livecodebench": 8.3,
"scicode": 5.2,
"aime": 3.3,
"ifbench": 26.2,
"tau2": 21.1,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 6,
"coding": 0,
"writing": 6,
"agentic": 32,
"overall": 9
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 2,
"speed": 2
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-3.2-3b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 8
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-3.1-70b-instruct",
"slug": "meta-llama/llama-3.1-70b-instruct",
"name": "Llama 3.1 70B Instruct",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Meta's class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...",
"created": 1721692800,
"created_human": "23 jul 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.4,
"completion_per_1m": 0.4,
"blended_per_1m": 0.4,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.40 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 36.2,
"ttft_seconds": 0.55
},
"benchmarks": {
"intelligence_index": 6.8,
"coding_index": null,
"math_index": 4,
"agentic_index": null,
"mmlu_pro": 67.6,
"gpqa": 40.9,
"hle": 4.6,
"livecodebench": 23.2,
"scicode": 26.7,
"aime": 4,
"ifbench": 34.4,
"tau2": 15.2,
"terminalbench": 3,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 0,
"writing": 11,
"agentic": 14,
"overall": 9
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 2
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-3.1-70b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 8
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-3.1-8b-instruct",
"slug": "meta-llama/llama-3.1-8b-instruct",
"name": "Llama 3.1 8B Instruct",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Meta's class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...",
"created": 1721692800,
"created_human": "23 jul 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.02,
"completion_per_1m": 0.03,
"blended_per_1m": 0.0225,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.02 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 196.9,
"ttft_seconds": 0.52
},
"benchmarks": {
"intelligence_index": 6.1,
"coding_index": null,
"math_index": 4.3,
"agentic_index": null,
"mmlu_pro": 47.6,
"gpqa": 25.9,
"hle": 5.1,
"livecodebench": 11.6,
"scicode": 13.2,
"aime": 4.3,
"ifbench": 28.6,
"tau2": 16.4,
"terminalbench": 0.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 9,
"coding": 0,
"writing": 9,
"agentic": 13,
"overall": 8
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-3.1-8b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 17
},
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen-2.5-coder-32b-instruct",
"slug": "qwen/qwen-2.5-coder-32b-instruct",
"name": "Qwen2.5 Coder 32B Instruct",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen2.5-Coder is the series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning…",
"created": 1731368400,
"created_human": "11 nov 2024",
"knowledge_cutoff": "2024-06-30",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.66,
"completion_per_1m": 1,
"blended_per_1m": 0.745,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.75 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 7.1,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 63.5,
"gpqa": 41.7,
"hle": 3.8,
"livecodebench": 29.5,
"scicode": 27.1,
"aime": 12,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 0,
"writing": 11,
"agentic": 0,
"overall": 7
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 6
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-4o-mini",
"slug": "openai/gpt-4o-mini",
"name": "GPT-4o-mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-4o mini is OpenAI's model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their advanced small model, it is many multiples more affordable...",
"created": 1721260800,
"created_human": "18 jul 2024",
"knowledge_cutoff": "2023-10-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 0.6,
"blended_per_1m": 0.2625,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.26 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 83.8,
"ttft_seconds": 0.62
},
"benchmarks": {
"intelligence_index": 6.9,
"coding_index": null,
"math_index": 14.7,
"agentic_index": null,
"mmlu_pro": 64.8,
"gpqa": 42.6,
"hle": 4,
"livecodebench": 23.4,
"scicode": 22.9,
"aime": 14.7,
"ifbench": 31,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 10,
"coding": 0,
"writing": 11,
"agentic": 0,
"overall": 7
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-4o-mini",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 10
},
"curated": false,
"pop_rank": null
},
{
"id": "liquid/lfm-2-24b-a2b",
"slug": "liquid/lfm-2-24b-a2b-20260224",
"name": "LFM2-24B-A2B",
"vendor": "LiquidAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per...",
"created": 1772048711,
"created_human": "25 feb 2026",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.03,
"completion_per_1m": 0.12,
"blended_per_1m": 0.0525,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.05 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 123.5,
"ttft_seconds": 0.3
},
"benchmarks": {
"intelligence_index": 4.9,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 47.4,
"hle": 4.4,
"livecodebench": null,
"scicode": 10.9,
"aime": null,
"ifbench": 45.9,
"tau2": 11.1,
"terminalbench": 0,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 7,
"coding": 0,
"writing": 7,
"agentic": 9,
"overall": 6
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 4
},
"popularity": 30,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/liquid/lfm-2-24b-a2b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "gemiddeld",
"label": "Gemiddelde prijs-kwaliteit",
"tone": "neutral",
"icon": "coins",
"desc": "Niet duur, niet goedkoop voor wat je krijgt.",
"score": 13
},
"curated": false,
"pop_rank": null
},
{
"id": "allenai/olmo-3-32b-think",
"slug": "allenai/olmo-3-32b-think-20251121",
"name": "Olmo 3 32B Think",
"vendor": "AllenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...",
"created": 1763758276,
"created_human": "21 nov 2025",
"knowledge_cutoff": null,
"context_length": 65536,
"context_human": "66K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 0.5,
"blended_per_1m": 0.2375,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.24 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 6.4,
"coding_index": null,
"math_index": 73.7,
"agentic_index": null,
"mmlu_pro": 75.9,
"gpqa": 61,
"hle": 5.9,
"livecodebench": 67.2,
"scicode": 28.6,
"aime": 73.7,
"ifbench": 49.1,
"tau2": 0,
"terminalbench": 1.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 9,
"coding": 0,
"writing": 9,
"agentic": 1,
"overall": 6
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/allenai/olmo-3-32b-think",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 9
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemma-3-27b-it",
"slug": "google/gemma-3-27b-it",
"name": "Gemma 3 27B",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
"created": 1741756359,
"created_human": "12 mrt 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.08,
"completion_per_1m": 0.16,
"blended_per_1m": 0.1,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.10 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 4.8,
"coding_index": null,
"math_index": 20.7,
"agentic_index": null,
"mmlu_pro": 66.9,
"gpqa": 42.8,
"hle": 4.7,
"livecodebench": 13.7,
"scicode": 21.2,
"aime": 20.7,
"ifbench": 31.8,
"tau2": 10.5,
"terminalbench": 3.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 7,
"coding": 0,
"writing": 7,
"agentic": 11,
"overall": 6
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 26,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemma-3-27b-it",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 10
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-saba",
"slug": "mistralai/mistral-saba-2502",
"name": "Saba",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...",
"created": 1739803239,
"created_human": "17 feb 2025",
"knowledge_cutoff": "2024-09-30",
"context_length": 32768,
"context_human": "33K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2,
"completion_per_1m": 0.6,
"blended_per_1m": 0.3,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.30 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 6.4,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 61.1,
"gpqa": 42.4,
"hle": 4.1,
"livecodebench": null,
"scicode": 24.1,
"aime": 13,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 9,
"coding": 0,
"writing": 9,
"agentic": 0,
"overall": 6
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 27,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-saba",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 8
},
"curated": false,
"pop_rank": null
},
{
"id": "anthropic/claude-3-haiku",
"slug": "anthropic/claude-3-haiku",
"name": "Claude 3 Haiku",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results here #multimodal",
"created": 1710288000,
"created_human": "13 mrt 2024",
"knowledge_cutoff": "2023-08-31",
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 1.25,
"blended_per_1m": 0.5,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.50 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 3.9,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": 37.4,
"hle": 3.9,
"livecodebench": 15.4,
"scicode": 18.6,
"aime": 1,
"ifbench": 36.1,
"tau2": 21.1,
"terminalbench": 0.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 6,
"coding": 0,
"writing": 6,
"agentic": 17,
"overall": 6
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 5
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/anthropic/claude-3-haiku",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 4
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-3.5-turbo-instruct",
"slug": "openai/gpt-3.5-turbo-instruct",
"name": "GPT-3.5 Turbo Instruct",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.",
"created": 1695859200,
"created_human": "28 sep 2023",
"knowledge_cutoff": "2021-09-30",
"context_length": 4095,
"context_human": "4K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.5,
"completion_per_1m": 2,
"blended_per_1m": 1.625,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.6 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 152.6,
"ttft_seconds": 0.76
},
"benchmarks": {
"intelligence_index": 3.6,
"coding_index": 10.7,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 46.2,
"gpqa": 29.7,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 5,
"coding": 13,
"writing": 5,
"agentic": 0,
"overall": 6
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 4
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/openai/gpt-3.5-turbo-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 2
},
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-3.5-turbo",
"slug": "openai/gpt-3.5-turbo",
"name": "GPT-3.5 Turbo",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.",
"created": 1685232000,
"created_human": "28 mei 2023",
"knowledge_cutoff": "2021-09-30",
"context_length": 16385,
"context_human": "16K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.5,
"completion_per_1m": 1.5,
"blended_per_1m": 0.75,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.75 per 1M tokens"
},
"speed": 4,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 152.6,
"ttft_seconds": 0.76
},
"benchmarks": {
"intelligence_index": 3.6,
"coding_index": 10.7,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 46.2,
"gpqa": 29.7,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 5,
"coding": 13,
"writing": 5,
"agentic": 0,
"overall": 6
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 4
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-3.5-turbo",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 3
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemma-3-12b-it",
"slug": "google/gemma-3-12b-it",
"name": "Gemma 3 12B",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
"created": 1741902625,
"created_human": "13 mrt 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.05,
"completion_per_1m": 0.15,
"blended_per_1m": 0.075,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.08 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 3.4,
"coding_index": null,
"math_index": 18.3,
"agentic_index": null,
"mmlu_pro": 59.5,
"gpqa": 34.9,
"hle": 4.8,
"livecodebench": 13.7,
"scicode": 17.4,
"aime": 18.3,
"ifbench": 36.7,
"tau2": 10.8,
"terminalbench": 0.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 5,
"coding": 0,
"writing": 5,
"agentic": 9,
"overall": 5
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemma-3-12b-it",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 8
},
"curated": false,
"pop_rank": null
},
{
"id": "microsoft/phi-4",
"slug": "microsoft/phi-4",
"name": "Phi 4",
"vendor": "Microsoft",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...",
"created": 1736489872,
"created_human": "10 jan 2025",
"knowledge_cutoff": "2024-06-30",
"context_length": 16384,
"context_human": "16K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.07,
"completion_per_1m": 0.14,
"blended_per_1m": 0.0875,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.09 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 42.1,
"ttft_seconds": 0.5
},
"benchmarks": {
"intelligence_index": 4.9,
"coding_index": null,
"math_index": 18,
"agentic_index": null,
"mmlu_pro": 71.4,
"gpqa": 57.5,
"hle": 4.1,
"livecodebench": 23.1,
"scicode": 26,
"aime": 18,
"ifbench": 23.5,
"tau2": 0,
"terminalbench": 3.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 7,
"coding": 0,
"writing": 7,
"agentic": 3,
"overall": 5
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 2
},
"popularity": 26,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/microsoft/phi-4",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 10
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-3.2-11b-vision-instruct",
"slug": "meta-llama/llama-3.2-11b-vision-instruct",
"name": "Llama 3.2 11B Vision Instruct",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...",
"created": 1727222400,
"created_human": "25 sep 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.345,
"completion_per_1m": 0.345,
"blended_per_1m": 0.345,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.35 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 85.7,
"ttft_seconds": 0.55
},
"benchmarks": {
"intelligence_index": 3.3,
"coding_index": null,
"math_index": 1.7,
"agentic_index": null,
"mmlu_pro": 46.4,
"gpqa": 22.1,
"hle": 5.2,
"livecodebench": 11,
"scicode": 11.2,
"aime": 1.7,
"ifbench": 30.4,
"tau2": 14.6,
"terminalbench": 0.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 5,
"coding": 0,
"writing": 5,
"agentic": 12,
"overall": 5
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-3.2-11b-vision-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 4
},
"curated": false,
"pop_rank": null
},
{
"id": "nousresearch/hermes-3-llama-3.1-70b",
"slug": "nousresearch/hermes-3-llama-3.1-70b",
"name": "Hermes 3 70B Instruct",
"vendor": "Nous Research",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...",
"created": 1723939200,
"created_human": "18 aug 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.7,
"completion_per_1m": 0.7,
"blended_per_1m": 0.7,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.70 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 30.2,
"ttft_seconds": 0.35
},
"benchmarks": {
"intelligence_index": 5.1,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 57.1,
"gpqa": 40.1,
"hle": 4.1,
"livecodebench": 18.8,
"scicode": 23.1,
"aime": 2.3,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 7,
"coding": 0,
"writing": 7,
"agentic": 0,
"overall": 5
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 2
},
"popularity": 26,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/nousresearch/hermes-3-llama-3.1-70b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 5
},
"curated": false,
"pop_rank": null
},
{
"id": "ibm-granite/granite-4.0-h-micro",
"slug": "ibm-granite/granite-4.0-h-micro",
"name": "Granite 4.0 Micro",
"vendor": "IBM",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the in a series of models released by IBM. They are fine-tuned for long...",
"created": 1760927695,
"created_human": "20 okt 2025",
"knowledge_cutoff": null,
"context_length": 131000,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.017,
"completion_per_1m": 0.112,
"blended_per_1m": 0.0408,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.04 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 2.4,
"coding_index": null,
"math_index": 6,
"agentic_index": null,
"mmlu_pro": 44.7,
"gpqa": 33.6,
"hle": 5.1,
"livecodebench": 18,
"scicode": 11.9,
"aime": 6,
"ifbench": 24.8,
"tau2": 12.6,
"terminalbench": 1.5,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 3,
"coding": 0,
"writing": 3,
"agentic": 11,
"overall": 4
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 5
},
"popularity": 24,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/ibm-granite/granite-4.0-h-micro",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 6
},
"curated": false,
"pop_rank": null
},
{
"id": "microsoft/phi-4-mini-instruct",
"slug": "microsoft/phi-4-mini-instruct",
"name": "Phi 4 Mini Instruct",
"vendor": "Microsoft",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...",
"created": 1760726049,
"created_human": "17 okt 2025",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.08,
"completion_per_1m": 0.35,
"blended_per_1m": 0.1475,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.15 per 1M tokens"
},
"speed": 2,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 45.6,
"ttft_seconds": 1.32
},
"benchmarks": {
"intelligence_index": 3,
"coding_index": null,
"math_index": 6.7,
"agentic_index": null,
"mmlu_pro": 46.5,
"gpqa": 33.1,
"hle": 4.2,
"livecodebench": 12.6,
"scicode": 10.8,
"aime": 6.7,
"ifbench": 21.1,
"tau2": 8.2,
"terminalbench": 0,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 4,
"coding": 0,
"writing": 4,
"agentic": 6,
"overall": 4
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 2
},
"popularity": 24,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/microsoft/phi-4-mini-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 5
},
"curated": false,
"pop_rank": null
},
{
"id": "rekaai/reka-flash-3",
"slug": "rekaai/reka-flash-3",
"name": "Reka Flash 3",
"vendor": "Reka",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...",
"created": 1741812813,
"created_human": "12 mrt 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 65536,
"context_human": "66K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.2,
"blended_per_1m": 0.125,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.13 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 96,
"ttft_seconds": 1.72
},
"benchmarks": {
"intelligence_index": 4.1,
"coding_index": null,
"math_index": 33.7,
"agentic_index": null,
"mmlu_pro": 66.9,
"gpqa": 52.9,
"hle": 5.1,
"livecodebench": 43.5,
"scicode": 26.7,
"aime": 33.7,
"ifbench": 30.4,
"tau2": 0,
"terminalbench": 0,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 6,
"coding": 0,
"writing": 6,
"agentic": 0,
"overall": 4
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/rekaai/reka-flash-3",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 8
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/mistral-large",
"slug": "mistralai/mistral-large",
"name": "Mistral Large",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....",
"created": 1708905600,
"created_human": "26 feb 2024",
"knowledge_cutoff": "2024-11-30",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 6,
"blended_per_1m": 3,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 4.4,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 51.5,
"gpqa": 35.1,
"hle": 3.4,
"livecodebench": 17.8,
"scicode": 20.8,
"aime": 0,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 6,
"coding": 0,
"writing": 6,
"agentic": 0,
"overall": 4
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 25,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/mistralai/mistral-large",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 2
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/codestral-2508",
"slug": "mistralai/codestral-2508",
"name": "Codestral 2508",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post",
"created": 1754079630,
"created_human": "1 aug 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 0.9,
"blended_per_1m": 0.45,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.45 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1063,
"code_elo": 1057,
"count": 6,
"top": [
{
"category": "3d",
"elo": 1099,
"rank": 76
},
{
"category": "uicomponent",
"elo": 1072,
"rank": 78
},
{
"category": "dataviz",
"elo": 1061,
"rank": 83
},
{
"category": "codecategories",
"elo": 1057,
"rank": 89
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 4,
"coding": 2,
"writing": 4,
"agentic": 0,
"overall": 3
},
"stars": {
"intelligence": 1,
"coding": 1,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 21,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/codestral-2508",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 3
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemma-3-4b-it",
"slug": "google/gemma-3-4b-it",
"name": "Gemma 3 4B",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
"created": 1741905510,
"created_human": "13 mrt 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.05,
"completion_per_1m": 0.1,
"blended_per_1m": 0.0625,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.06 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": 1.1,
"coding_index": null,
"math_index": 12.7,
"agentic_index": null,
"mmlu_pro": 41.7,
"gpqa": 29.1,
"hle": 5.2,
"livecodebench": 11.2,
"scicode": 7.3,
"aime": 12.7,
"ifbench": 28.3,
"tau2": 5,
"terminalbench": 0.8,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 4,
"overall": 2
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 1,
"speed": 3
},
"popularity": 24,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/google/gemma-3-4b-it",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 3
},
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/ministral-3b-2512",
"slug": "mistralai/ministral-3b-2512",
"name": "Ministral 3 3B 2512",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.",
"created": 1764681560,
"created_human": "2 dec 2025",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.1,
"blended_per_1m": 0.1,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.10 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": 4.8,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 1047,
"code_elo": 1060,
"count": 4,
"top": [
{
"category": "3d",
"elo": 1041,
"rank": 86
},
{
"category": "codecategories",
"elo": 1060,
"rank": 88
},
{
"category": "website",
"elo": 1071,
"rank": 89
},
{
"category": "gamedev",
"elo": 1016,
"rank": 96
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 6,
"writing": 0,
"agentic": 0,
"overall": 1
},
"stars": {
"intelligence": 0,
"coding": 1,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 18,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/ministral-3b-2512",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-3.2-1b-instruct",
"slug": "meta-llama/llama-3.2-1b-instruct",
"name": "Llama 3.2 1B Instruct",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...",
"created": 1727222400,
"created_human": "25 sep 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.027,
"completion_per_1m": 0.201,
"blended_per_1m": 0.0705,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.07 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 87.5,
"ttft_seconds": 0.6
},
"benchmarks": {
"intelligence_index": 1.1,
"coding_index": null,
"math_index": 0,
"agentic_index": null,
"mmlu_pro": 20,
"gpqa": 19.6,
"hle": 5.3,
"livecodebench": 1.9,
"scicode": 1.7,
"aime": 0,
"ifbench": 22.8,
"tau2": 0,
"terminalbench": 0,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 0,
"overall": 1
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 24,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-3.2-1b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 3
},
"curated": false,
"pop_rank": null
},
{
"id": "meta-llama/llama-3-8b-instruct",
"slug": "meta-llama/llama-3-8b-instruct",
"name": "Llama 3 8B Instruct",
"vendor": "Meta",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Meta's class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...",
"created": 1713398400,
"created_human": "18 apr 2024",
"knowledge_cutoff": "2023-12-31",
"context_length": 8192,
"context_human": "8K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.14,
"completion_per_1m": 0.14,
"blended_per_1m": 0.14,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.14 per 1M tokens"
},
"speed": 3,
"speed_source": "measured",
"performance": {
"tokens_per_sec": 81.5,
"ttft_seconds": 0.48
},
"benchmarks": {
"intelligence_index": 1.2,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": 40.5,
"gpqa": 29.6,
"hle": 5.1,
"livecodebench": 9.6,
"scicode": 11.9,
"aime": 0,
"ifbench": 24.6,
"tau2": 0,
"terminalbench": 0,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 2,
"coding": 0,
"writing": 2,
"agentic": 0,
"overall": 1
},
"stars": {
"intelligence": 1,
"coding": 0,
"writing": 1,
"agentic": 0,
"speed": 3
},
"popularity": 24,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/meta-llama/llama-3-8b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "benchmark"
},
"value": {
"key": "duur",
"label": "Relatief duur",
"tone": "red",
"icon": "coins",
"desc": "Je betaalt veel voor weinig extra kwaliteit — er zijn voordeligere alternatieven.",
"score": 2
},
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-3.1-flash-image",
"slug": "google/gemini-3.1-flash-image-20260528",
"name": "Nano Banana 2 (Gemini 3.1 Flash Image)",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...",
"created": 1781754065,
"created_human": "18 jun 2026",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": true,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.5,
"completion_per_1m": 3,
"blended_per_1m": 1.125,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.1 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 20,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3.1-flash-image",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-3-pro-image",
"slug": "google/gemini-3-pro-image-20260528",
"name": "Nano Banana Pro (Gemini 3 Pro Image)",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Nano Banana Pro is Google’s advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
"created": 1781754054,
"created_human": "18 jun 2026",
"knowledge_cutoff": null,
"context_length": 65536,
"context_human": "66K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": true,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 12,
"blended_per_1m": 4.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.5 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 20,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3-pro-image",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "cohere/north-mini-code:free",
"slug": "cohere/north-mini-code-20260617",
"name": "North Mini Code (free)",
"vendor": "Cohere",
"origin": {
"country": "Canada",
"country_code": "CA",
"flag": "🇨🇦",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...",
"created": 1781723748,
"created_human": "17 jun 2026",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 20,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"free",
"fast"
],
"openrouter_url": "https://openrouter.ai/cohere/north-mini-code:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~anthropic/claude-fable-latest",
"slug": "~anthropic/claude-fable-latest",
"name": "Claude Fable Latest",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the Claude Fable family.",
"created": 1781029944,
"created_human": "9 jun 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 10,
"completion_per_1m": 50,
"blended_per_1m": 20,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$20 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 19,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/~anthropic/claude-fable-latest",
"available": false,
"unavailable_reason": "Dit model is momenteel niet beschikbaar.",
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-3.5-content-safety:free",
"slug": "nvidia/nemotron-3.5-content-safety-20260604",
"name": "Nemotron 3.5 Content Safety (free)",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...",
"created": 1780581864,
"created_human": "4 jun 2026",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 19,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "x-ai/grok-build-0.1",
"slug": "x-ai/grok-build-0.1-20260520",
"name": "Grok Build 0.1",
"vendor": "xAI (Grok)",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...",
"created": 1779298123,
"created_human": "20 mei 2026",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1,
"completion_per_1m": 2,
"blended_per_1m": 1.25,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.3 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 18,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/x-ai/grok-build-0.1",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "perceptron/perceptron-mk1",
"slug": "perceptron/perceptron-mk1-20260512",
"name": "Perceptron Mk1",
"vendor": "Perceptron",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...",
"created": 1778597029,
"created_human": "12 mei 2026",
"knowledge_cutoff": null,
"context_length": 32768,
"context_human": "33K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.15,
"completion_per_1m": 1.5,
"blended_per_1m": 0.4875,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.49 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 17,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/perceptron/perceptron-mk1",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-chat-latest",
"slug": "openai/gpt-chat-latest-20260505",
"name": "GPT Chat Latest",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT Chat points to OpenAI's stable API alias `chat-latest` that always resolves to the Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...",
"created": 1778000212,
"created_human": "5 mei 2026",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 30,
"blended_per_1m": 11.25,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$11 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 17,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-chat-latest",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openrouter/owl-alpha",
"slug": "openrouter/owl-alpha",
"name": "Owl Alpha",
"vendor": "Openrouter",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution....",
"created": 1777398589,
"created_human": "28 apr 2026",
"knowledge_cutoff": null,
"context_length": 1048756,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten"
],
"categories": [
"long-context",
"free"
],
"openrouter_url": "https://openrouter.ai/openrouter/owl-alpha",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
"slug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428",
"name": "Nemotron 3 Nano Omni (free)",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...",
"created": 1777393095,
"created_human": "28 apr 2026",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"free",
"fast"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "poolside/laguna-xs.2:free",
"slug": "poolside/laguna-xs.2-20260421",
"name": "Laguna XS.2 (free)",
"vendor": "Poolside",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Laguna XS.2 is the second-generation model in the XS size class from Poolside, their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...",
"created": 1777389604,
"created_human": "28 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/poolside/laguna-xs.2:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "poolside/laguna-xs.2",
"slug": "poolside/laguna-xs.2-20260421",
"name": "Laguna XS.2",
"vendor": "Poolside",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Laguna XS.2 is the second-generation model in the XS size class from Poolside, their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...",
"created": 1777389604,
"created_human": "28 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.2,
"blended_per_1m": 0.125,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.13 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/poolside/laguna-xs.2",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "poolside/laguna-m.1:free",
"slug": "poolside/laguna-m.1-20260312",
"name": "Laguna M.1 (free)",
"vendor": "Poolside",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Laguna M.1 is the flagship coding agent model from Poolside, optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...",
"created": 1777388504,
"created_human": "28 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/poolside/laguna-m.1:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "poolside/laguna-m.1",
"slug": "poolside/laguna-m.1-20260312",
"name": "Laguna M.1",
"vendor": "Poolside",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Laguna M.1 is the flagship coding agent model from Poolside, optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...",
"created": 1777388504,
"created_human": "28 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.2,
"completion_per_1m": 0.4,
"blended_per_1m": 0.25,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.25 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/poolside/laguna-m.1",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~anthropic/claude-haiku-latest",
"slug": "~anthropic/claude-haiku-latest",
"name": "Anthropic Claude Haiku Latest",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the Anthropic Claude Haiku family.",
"created": 1777318492,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1,
"completion_per_1m": 5,
"blended_per_1m": 2,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$2.0 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/~anthropic/claude-haiku-latest",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~openai/gpt-mini-latest",
"slug": "~openai/gpt-mini-latest",
"name": "OpenAI GPT Mini Latest",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the OpenAI GPT Mini family.",
"created": 1777318471,
"created_human": "27 apr 2026",
"knowledge_cutoff": "2025-08-31",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.75,
"completion_per_1m": 4.5,
"blended_per_1m": 1.6875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.7 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/~openai/gpt-mini-latest",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~google/gemini-pro-latest",
"slug": "~google/gemini-pro-latest",
"name": "Google Gemini Pro Latest",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the Google Gemini Pro family.",
"created": 1777318451,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 12,
"blended_per_1m": 4.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.5 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/~google/gemini-pro-latest",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~moonshotai/kimi-latest",
"slug": "~moonshotai/kimi-latest",
"name": "MoonshotAI Kimi Latest",
"vendor": "Moonshot AI",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "This model always redirects to the model in the MoonshotAI Kimi family.",
"created": 1777318428,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.66,
"completion_per_1m": 3.41,
"blended_per_1m": 1.3475,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.3 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/~moonshotai/kimi-latest",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~google/gemini-flash-latest",
"slug": "~google/gemini-flash-latest",
"name": "Google Gemini Flash Latest",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the Google Gemini Flash family.",
"created": 1777318398,
"created_human": "27 apr 2026",
"knowledge_cutoff": "2025-01-01",
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.5,
"completion_per_1m": 9,
"blended_per_1m": 3.375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context",
"fast"
],
"openrouter_url": "https://openrouter.ai/~google/gemini-flash-latest",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~anthropic/claude-sonnet-latest",
"slug": "~anthropic/claude-sonnet-latest",
"name": "Anthropic Claude Sonnet Latest",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the Anthropic Claude Sonnet family.",
"created": 1777318368,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 3,
"completion_per_1m": 15,
"blended_per_1m": 6,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$6.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/~anthropic/claude-sonnet-latest",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~openai/gpt-latest",
"slug": "~openai/gpt-latest",
"name": "OpenAI GPT Latest",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the OpenAI GPT family.",
"created": 1777318334,
"created_human": "27 apr 2026",
"knowledge_cutoff": "2025-12-01",
"context_length": 1050000,
"context_human": "1.1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 30,
"blended_per_1m": 11.25,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$11 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/~openai/gpt-latest",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-plus-20260420",
"slug": "qwen/qwen3.5-plus-20260420",
"name": "Qwen3.5 Plus 2026-04-20",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...",
"created": 1777261368,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 1.8,
"blended_per_1m": 0.675,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.68 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-plus-20260420",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.6-flash",
"slug": "qwen/qwen3.6-flash",
"name": "Qwen3.6 Flash",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...",
"created": 1777261362,
"created_human": "27 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1875,
"completion_per_1m": 1.125,
"blended_per_1m": 0.4219,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.42 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.6-flash",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5.5-pro",
"slug": "openai/gpt-5.5-pro-20260423",
"name": "GPT-5.5 Pro",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...",
"created": 1777051896,
"created_human": "24 apr 2026",
"knowledge_cutoff": "2025-12-01",
"context_length": 1050000,
"context_human": "1.1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 30,
"completion_per_1m": 180,
"blended_per_1m": 67.5,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$68 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 31,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.5-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5.4-image-2",
"slug": "openai/gpt-5.4-image-2-20260421",
"name": "GPT-5.4 Image 2",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...",
"created": 1776797528,
"created_human": "21 apr 2026",
"knowledge_cutoff": null,
"context_length": 272000,
"context_human": "272K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": true,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 8,
"completion_per_1m": 15,
"blended_per_1m": 9.75,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$9.8 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen",
"Afbeeldingen maken"
],
"categories": [
"vision",
"image-gen",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.4-image-2",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "~anthropic/claude-opus-latest",
"slug": "~anthropic/claude-opus-latest",
"name": "Claude Opus Latest",
"vendor": "Anthropic",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "This model always redirects to the model in the Claude Opus family.",
"created": 1776795361,
"created_human": "21 apr 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 5,
"completion_per_1m": 25,
"blended_per_1m": 10,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$10 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 16,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/~anthropic/claude-opus-latest",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "x-ai/grok-4.20-multi-agent",
"slug": "x-ai/grok-4.20-multi-agent-20260309",
"name": "Grok 4.20 Multi-Agent",
"vendor": "xAI (Grok)",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...",
"created": 1774979158,
"created_human": "31 mrt 2026",
"knowledge_cutoff": "2025-09-01",
"context_length": 2000000,
"context_human": "2M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 2.5,
"blended_per_1m": 1.5625,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.6 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 14,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/x-ai/grok-4.20-multi-agent",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "google/lyria-3-pro-preview",
"slug": "google/lyria-3-pro-preview-20260330",
"name": "Lyria 3 Pro Preview",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...",
"created": 1774907286,
"created_human": "30 mrt 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": true,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 14,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"long-context",
"free"
],
"openrouter_url": "https://openrouter.ai/google/lyria-3-pro-preview",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "google/lyria-3-clip-preview",
"slug": "google/lyria-3-clip-preview-20260330",
"name": "Lyria 3 Clip Preview",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...",
"created": 1774907255,
"created_human": "30 mrt 2026",
"knowledge_cutoff": null,
"context_length": 1048576,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": true,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 14,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"long-context",
"free"
],
"openrouter_url": "https://openrouter.ai/google/lyria-3-clip-preview",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "rekaai/reka-edge",
"slug": "rekaai/reka-edge-2603",
"name": "Reka Edge",
"vendor": "Reka",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...",
"created": 1774026965,
"created_human": "20 mrt 2026",
"knowledge_cutoff": null,
"context_length": 16384,
"context_human": "16K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.1,
"blended_per_1m": 0.1,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.10 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 13,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/rekaai/reka-edge",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "bytedance-seed/seed-2.0-lite",
"slug": "bytedance-seed/seed-2.0-lite-20260309",
"name": "Seed-2.0-Lite",
"vendor": "ByteDance",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...",
"created": 1773157231,
"created_human": "10 mrt 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 2,
"blended_per_1m": 0.6875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.69 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 13,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/bytedance-seed/seed-2.0-lite",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5.4-pro",
"slug": "openai/gpt-5.4-pro-20260305",
"name": "GPT-5.4 Pro",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.4 Pro is OpenAI's advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...",
"created": 1772734366,
"created_human": "5 mrt 2026",
"knowledge_cutoff": null,
"context_length": 1050000,
"context_human": "1.1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 30,
"completion_per_1m": 180,
"blended_per_1m": 67.5,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$68 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 28,
"data_sources": [
"openrouter",
"artificial_analysis"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.4-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5.3-chat",
"slug": "openai/gpt-5.3-chat-20260303",
"name": "GPT-5.3 Chat",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...",
"created": 1772564061,
"created_human": "3 mrt 2026",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.75,
"completion_per_1m": 14,
"blended_per_1m": 4.8125,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.8 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 12,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.3-chat",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "bytedance-seed/seed-2.0-mini",
"slug": "bytedance-seed/seed-2.0-mini-20260224",
"name": "Seed-2.0-Mini",
"vendor": "ByteDance",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four r…",
"created": 1772131107,
"created_human": "26 feb 2026",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.4,
"blended_per_1m": 0.175,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.18 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 12,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/bytedance-seed/seed-2.0-mini",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3.5-flash-02-23",
"slug": "qwen/qwen3.5-flash-20260224",
"name": "Qwen3.5-Flash",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...",
"created": 1772053776,
"created_human": "25 feb 2026",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.065,
"completion_per_1m": 0.26,
"blended_per_1m": 0.1138,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.11 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 12,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3.5-flash-02-23",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "google/gemini-3.1-pro-preview-customtools",
"slug": "google/gemini-3.1-pro-preview-customtools-20260219",
"name": "Gemini 3.1 Pro Preview Custom Tools",
"vendor": "Google",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...",
"created": 1772045923,
"created_human": "25 feb 2026",
"knowledge_cutoff": null,
"context_length": 1048756,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": true,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 12,
"blended_per_1m": 4.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.5 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 12,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen",
"Spraak & audio"
],
"categories": [
"vision",
"audio",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/google/gemini-3.1-pro-preview-customtools",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "aion-labs/aion-2.0",
"slug": "aion-labs/aion-2.0-20260223",
"name": "Aion-2.0",
"vendor": "Aion-labs",
"origin": {
"country": "Onbekend",
"country_code": "",
"flag": "🌐",
"region": "other",
"region_label": "Overig / community",
"eu": false
},
"description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....",
"created": 1771881306,
"created_human": "23 feb 2026",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.8,
"completion_per_1m": 1.6,
"blended_per_1m": 1,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 12,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/aion-labs/aion-2.0",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openrouter/free",
"slug": "openrouter/free",
"name": "Free Models Router",
"vendor": "Openrouter",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...",
"created": 1769917427,
"created_human": "1 feb 2026",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 10,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"free"
],
"openrouter_url": "https://openrouter.ai/openrouter/free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "minimax/minimax-m2-her",
"slug": "minimax/minimax-m2-her-20260123",
"name": "MiniMax M2-her",
"vendor": "MiniMax",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...",
"created": 1769177239,
"created_human": "23 jan 2026",
"knowledge_cutoff": null,
"context_length": 65536,
"context_human": "66K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 1.2,
"blended_per_1m": 0.525,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.53 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 9,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/minimax/minimax-m2-her",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "writer/palmyra-x5",
"slug": "writer/palmyra-x5-20250428",
"name": "Palmyra X5",
"vendor": "Writer",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Palmyra X5 is Writer's advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...",
"created": 1769003823,
"created_human": "21 jan 2026",
"knowledge_cutoff": null,
"context_length": 1040000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.6,
"completion_per_1m": 6,
"blended_per_1m": 1.95,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$2.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 9,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten"
],
"categories": [
"long-context"
],
"openrouter_url": "https://openrouter.ai/writer/palmyra-x5",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "liquid/lfm-2.5-1.2b-thinking:free",
"slug": "liquid/lfm-2.5-1.2b-thinking-20260120",
"name": "LFM2.5-1.2B-Thinking (free)",
"vendor": "LiquidAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...",
"created": 1768927527,
"created_human": "20 jan 2026",
"knowledge_cutoff": null,
"context_length": 32768,
"context_human": "33K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 9,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"free"
],
"openrouter_url": "https://openrouter.ai/liquid/lfm-2.5-1.2b-thinking:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "liquid/lfm-2.5-1.2b-instruct:free",
"slug": "liquid/lfm-2.5-1.2b-instruct-20260120",
"name": "LFM2.5-1.2B-Instruct (free)",
"vendor": "LiquidAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.",
"created": 1768927521,
"created_human": "20 jan 2026",
"knowledge_cutoff": null,
"context_length": 32768,
"context_human": "33K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 9,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"free"
],
"openrouter_url": "https://openrouter.ai/liquid/lfm-2.5-1.2b-instruct:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-audio",
"slug": "openai/gpt-audio",
"name": "GPT Audio",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...",
"created": 1768862569,
"created_human": "19 jan 2026",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": true,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": true,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2.5,
"completion_per_1m": 10,
"blended_per_1m": 4.375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$4.4 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 9,
"data_sources": [
"openrouter"
],
"use_cases": [
"Spraak & audio"
],
"categories": [
"audio"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-audio",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-audio-mini",
"slug": "openai/gpt-audio-mini",
"name": "GPT Audio Mini",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...",
"created": 1768859419,
"created_human": "19 jan 2026",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": true,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": true,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.6,
"completion_per_1m": 2.4,
"blended_per_1m": 1.05,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.1 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 9,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Spraak & audio"
],
"categories": [
"audio",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-audio-mini",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "bytedance-seed/seed-1.6-flash",
"slug": "bytedance-seed/seed-1.6-flash-20250625",
"name": "Seed 1.6 Flash",
"vendor": "ByteDance",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...",
"created": 1766505011,
"created_human": "23 dec 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.075,
"completion_per_1m": 0.3,
"blended_per_1m": 0.1313,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.13 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/bytedance-seed/seed-1.6-flash",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "bytedance-seed/seed-1.6",
"slug": "bytedance-seed/seed-1.6-20250625",
"name": "Seed 1.6",
"vendor": "ByteDance",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.",
"created": 1766504997,
"created_human": "23 dec 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.25,
"completion_per_1m": 2,
"blended_per_1m": 0.6875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.69 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/bytedance-seed/seed-1.6",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-3-nano-30b-a3b:free",
"slug": "nvidia/nemotron-3-nano-30b-a3b",
"name": "Nemotron 3 Nano 30B A3B (free)",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...",
"created": 1765731275,
"created_human": "14 dec 2025",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"free",
"fast"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-3-nano-30b-a3b",
"slug": "nvidia/nemotron-3-nano-30b-a3b",
"name": "Nemotron 3 Nano 30B A3B",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...",
"created": 1765731275,
"created_human": "14 dec 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.05,
"completion_per_1m": 0.2,
"blended_per_1m": 0.0875,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.09 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5.2-pro",
"slug": "openai/gpt-5.2-pro-20251211",
"name": "GPT-5.2 Pro",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.2 Pro is OpenAI’s advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...",
"created": 1765389780,
"created_human": "10 dec 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 21,
"completion_per_1m": 168,
"blended_per_1m": 57.75,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$58 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.2-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/devstral-2512",
"slug": "mistralai/devstral-2512",
"name": "Devstral 2 2512",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...",
"created": 1765285419,
"created_human": "9 dec 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.4,
"completion_per_1m": 2,
"blended_per_1m": 0.8,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.80 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/devstral-2512",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "relace/relace-search",
"slug": "relace/relace-search-20251208",
"name": "Relace Search",
"vendor": "Relace",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...",
"created": 1765213560,
"created_human": "8 dec 2025",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1,
"completion_per_1m": 3,
"blended_per_1m": 1.5,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.5 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/relace/relace-search",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5.1-codex-max",
"slug": "openai/gpt-5.1-codex-max-20251204",
"name": "GPT-5.1-Codex-Max",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5.1-Codex-Max is OpenAI’s agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...",
"created": 1764878934,
"created_human": "4 dec 2025",
"knowledge_cutoff": null,
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 10,
"blended_per_1m": 3.4375,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.4 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5.1-codex-max",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "amazon/nova-2-lite-v1",
"slug": "amazon/nova-2-lite-v1",
"name": "Nova 2 Lite",
"vendor": "Amazon",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...",
"created": 1764696672,
"created_human": "2 dec 2025",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 2.5,
"blended_per_1m": 0.85,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.85 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/amazon/nova-2-lite-v1",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "arcee-ai/trinity-mini",
"slug": "arcee-ai/trinity-mini-20251201",
"name": "Trinity Mini",
"vendor": "Arcee AI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...",
"created": 1764601720,
"created_human": "1 dec 2025",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.045,
"completion_per_1m": 0.15,
"blended_per_1m": 0.0713,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.07 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/arcee-ai/trinity-mini",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "deepcogito/cogito-v2.1-671b",
"slug": "deepcogito/cogito-v2.1-671b-20251118",
"name": "Cogito v2.1 671B",
"vendor": "Deepcogito",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...",
"created": 1763071233,
"created_human": "13 nov 2025",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1.25,
"completion_per_1m": 1.25,
"blended_per_1m": 1.25,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.3 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/deepcogito/cogito-v2.1-671b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "amazon/nova-premier-v1",
"slug": "amazon/nova-premier-v1",
"name": "Nova Premier 1.0",
"vendor": "Amazon",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Amazon Nova Premier is the highly capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.",
"created": 1761950332,
"created_human": "31 okt 2025",
"knowledge_cutoff": null,
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2.5,
"completion_per_1m": 12.5,
"blended_per_1m": 5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$5.0 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": 879,
"code_elo": null,
"count": 1,
"top": [
{
"category": "website",
"elo": 879,
"rank": 107
}
]
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 15,
"data_sources": [
"openrouter",
"design_arena"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"long-context"
],
"openrouter_url": "https://openrouter.ai/amazon/nova-premier-v1",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "perplexity/sonar-pro-search",
"slug": "perplexity/sonar-pro-search",
"name": "Sonar Pro Search",
"vendor": "Perplexity",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...",
"created": 1761854366,
"created_human": "30 okt 2025",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 3,
"completion_per_1m": 15,
"blended_per_1m": 6,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$6.0 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/perplexity/sonar-pro-search",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "mistralai/voxtral-small-24b-2507",
"slug": "mistralai/voxtral-small-24b-2507",
"name": "Voxtral Small 24B 2507",
"vendor": "Mistral AI",
"origin": {
"country": "Frankrijk",
"country_code": "FR",
"flag": "🇫🇷",
"region": "europe",
"region_label": "Europa",
"eu": true
},
"description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input aud…",
"created": 1761835144,
"created_human": "30 okt 2025",
"knowledge_cutoff": null,
"context_length": 32000,
"context_human": "32K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": true,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.3,
"blended_per_1m": 0.15,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.15 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Spraak & audio"
],
"categories": [
"audio",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/mistralai/voxtral-small-24b-2507",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-oss-safeguard-20b",
"slug": "openai/gpt-oss-safeguard-20b",
"name": "gpt-oss-safeguard-20b",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and tr…",
"created": 1761752836,
"created_human": "29 okt 2025",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.075,
"completion_per_1m": 0.3,
"blended_per_1m": 0.1313,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.13 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-oss-safeguard-20b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-nano-12b-v2-vl:free",
"slug": "nvidia/nemotron-nano-12b-v2-vl",
"name": "Nemotron Nano 12B 2 VL (free)",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy w…",
"created": 1761675565,
"created_human": "28 okt 2025",
"knowledge_cutoff": null,
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": true,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"free",
"fast"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/o3-deep-research",
"slug": "openai/o3-deep-research-2025-06-26",
"name": "o3 Deep Research",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.",
"created": 1760129661,
"created_human": "10 okt 2025",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 10,
"completion_per_1m": 40,
"blended_per_1m": 17.5,
"currency": "USD"
},
"cost_tier": {
"level": 4,
"label": "Hoog",
"color": "error",
"detail": "±$18 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning"
],
"openrouter_url": "https://openrouter.ai/openai/o3-deep-research",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/o4-mini-deep-research",
"slug": "openai/o4-mini-deep-research-2025-06-26",
"name": "o4 Mini Deep Research",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.",
"created": 1760129642,
"created_human": "10 okt 2025",
"knowledge_cutoff": null,
"context_length": 200000,
"context_human": "200K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 8,
"blended_per_1m": 3.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.5 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"fast"
],
"openrouter_url": "https://openrouter.ai/openai/o4-mini-deep-research",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
"slug": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
"name": "Llama 3.3 Nemotron Super 49B V1.5",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, c…",
"created": 1760101395,
"created_human": "10 okt 2025",
"knowledge_cutoff": "2024-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.4,
"completion_per_1m": 0.4,
"blended_per_1m": 0.4,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.40 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/nvidia/llama-3.3-nemotron-super-49b-v1.5",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "openai/gpt-5-pro",
"slug": "openai/gpt-5-pro-2025-10-06",
"name": "GPT-5 Pro",
"vendor": "OpenAI",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "GPT-5 Pro is OpenAI’s advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...",
"created": 1759776663,
"created_human": "6 okt 2025",
"knowledge_cutoff": "2024-09-30",
"context_length": 400000,
"context_human": "400K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": true,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 15,
"completion_per_1m": 120,
"blended_per_1m": 41.25,
"currency": "USD"
},
"cost_tier": {
"level": 5,
"label": "Zeer hoog",
"color": "error",
"detail": "±$41 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten",
"Afbeeldingen lezen"
],
"categories": [
"vision",
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/openai/gpt-5-pro",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "thedrummer/cydonia-24b-v4.1",
"slug": "thedrummer/cydonia-24b-v4.1",
"name": "Cydonia 24B V4.1",
"vendor": "Thedrummer",
"origin": {
"country": "Onbekend",
"country_code": "",
"flag": "🌐",
"region": "other",
"region_label": "Overig / community",
"eu": false
},
"description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.",
"created": 1758931878,
"created_human": "27 sep 2025",
"knowledge_cutoff": "2024-04-30",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.3,
"completion_per_1m": 0.5,
"blended_per_1m": 0.35,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.35 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/thedrummer/cydonia-24b-v4.1",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "relace/relace-apply-3",
"slug": "relace/relace-apply-3",
"name": "Relace Apply 3",
"vendor": "Relace",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...",
"created": 1758891572,
"created_human": "26 sep 2025",
"knowledge_cutoff": null,
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.85,
"completion_per_1m": 1.25,
"blended_per_1m": 0.95,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$0.95 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"budget"
],
"openrouter_url": "https://openrouter.ai/relace/relace-apply-3",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-coder-plus",
"slug": "qwen/qwen3-coder-plus",
"name": "Qwen3 Coder Plus",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...",
"created": 1758662707,
"created_human": "23 sep 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.65,
"completion_per_1m": 3.25,
"blended_per_1m": 1.3,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.3 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten"
],
"categories": [
"reasoning",
"long-context"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-coder-plus",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-coder-flash",
"slug": "qwen/qwen3-coder-flash",
"name": "Qwen3 Coder Flash",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...",
"created": 1758115536,
"created_human": "17 sep 2025",
"knowledge_cutoff": "2025-06-30",
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.195,
"completion_per_1m": 0.975,
"blended_per_1m": 0.39,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.39 per 1M tokens"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice",
"Lange documenten"
],
"categories": [
"long-context",
"fast",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-coder-flash",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen3-next-80b-a3b-instruct:free",
"slug": "qwen/qwen3-next-80b-a3b-instruct-2509",
"name": "Qwen3 Next 80B A3B Instruct (free)",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multili…",
"created": 1757612213,
"created_human": "11 sep 2025",
"knowledge_cutoff": "2025-09-30",
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"free"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen-plus-2025-07-28:thinking",
"slug": "qwen/qwen-plus-2025-07-28",
"name": "Qwen Plus 0728 (thinking)",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.",
"created": 1757347599,
"created_human": "8 sep 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.26,
"completion_per_1m": 0.78,
"blended_per_1m": 0.39,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.39 per 1M tokens"
},
"speed": 2,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 2
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten"
],
"categories": [
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen-plus-2025-07-28:thinking",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "qwen/qwen-plus-2025-07-28",
"slug": "qwen/qwen-plus-2025-07-28",
"name": "Qwen Plus 0728",
"vendor": "Alibaba (Qwen)",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.",
"created": 1757347599,
"created_human": "8 sep 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 1000000,
"context_human": "1M tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.26,
"completion_per_1m": 0.78,
"blended_per_1m": 0.39,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.39 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Lange documenten"
],
"categories": [
"reasoning",
"long-context",
"budget"
],
"openrouter_url": "https://openrouter.ai/qwen/qwen-plus-2025-07-28",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nvidia/nemotron-nano-9b-v2:free",
"slug": "nvidia/nemotron-nano-9b-v2",
"name": "Nemotron Nano 9B V2 (free)",
"vendor": "NVIDIA",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...",
"created": 1757106807,
"created_human": "5 sep 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 5,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 5
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Chat & klantenservice"
],
"categories": [
"reasoning",
"free",
"fast"
],
"openrouter_url": "https://openrouter.ai/nvidia/nemotron-nano-9b-v2:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nousresearch/hermes-4-70b",
"slug": "nousresearch/hermes-4-70b",
"name": "Hermes 4 70B",
"vendor": "Nous Research",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...",
"created": 1756236182,
"created_human": "26 aug 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.13,
"completion_per_1m": 0.4,
"blended_per_1m": 0.1975,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.20 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/nousresearch/hermes-4-70b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "nousresearch/hermes-4-405b",
"slug": "nousresearch/hermes-4-405b",
"name": "Hermes 4 405B",
"vendor": "Nous Research",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...",
"created": 1756235463,
"created_human": "26 aug 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 1,
"completion_per_1m": 3,
"blended_per_1m": 1.5,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.5 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/nousresearch/hermes-4-405b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "ai21/jamba-large-1.7",
"slug": "ai21/jamba-large-1.7",
"name": "Jamba Large 1.7",
"vendor": "AI21",
"origin": {
"country": "Israël",
"country_code": "IL",
"flag": "🇮🇱",
"region": "asia",
"region_label": "Azië (overig)",
"eu": false
},
"description": "Jamba Large 1.7 is the model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...",
"created": 1754669020,
"created_human": "8 aug 2025",
"knowledge_cutoff": "2024-08-31",
"context_length": 256000,
"context_human": "256K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 2,
"completion_per_1m": 8,
"blended_per_1m": 3.5,
"currency": "USD"
},
"cost_tier": {
"level": 3,
"label": "Gemiddeld",
"color": "warning",
"detail": "±$3.5 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/ai21/jamba-large-1.7",
"available": true,
"tier": {
"key": "standaard",
"label": "Standaard",
"sublabel": "voor dagelijks werk",
"icon": "compass",
"desc": "Ruim voldoende voor de meeste dagelijkse taken, en een stuk voordeliger dan de topklasse.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "bytedance/ui-tars-1.5-7b",
"slug": "bytedance/ui-tars-1.5-7b",
"name": "UI-TARS 7B",
"vendor": "ByteDance",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...",
"created": 1753205056,
"created_human": "22 jul 2025",
"knowledge_cutoff": "2025-01-31",
"context_length": 128000,
"context_human": "128K tokens",
"capabilities": {
"text": true,
"vision": true,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.1,
"completion_per_1m": 0.2,
"blended_per_1m": 0.125,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.13 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Afbeeldingen lezen"
],
"categories": [
"vision",
"budget"
],
"openrouter_url": "https://openrouter.ai/bytedance/ui-tars-1.5-7b",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "switchpoint/router",
"slug": "switchpoint/router",
"name": "Switchpoint Router",
"vendor": "Switchpoint",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you...",
"created": 1752272899,
"created_human": "11 jul 2025",
"knowledge_cutoff": null,
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.85,
"completion_per_1m": 3.4,
"blended_per_1m": 1.4875,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.5 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning"
],
"openrouter_url": "https://openrouter.ai/switchpoint/router",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
"slug": "venice/uncensored",
"name": "Uncensored (free)",
"vendor": "Cognitivecomputations",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preservi…",
"created": 1752094966,
"created_human": "9 jul 2025",
"knowledge_cutoff": "2024-04-30",
"context_length": 32768,
"context_human": "33K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": true,
"pricing": {
"prompt_per_1m": 0,
"completion_per_1m": 0,
"blended_per_1m": 0,
"currency": "USD"
},
"cost_tier": {
"level": 0,
"label": "Gratis",
"color": "success",
"detail": "€0 — gratis te gebruiken"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"free"
],
"openrouter_url": "https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "tencent/hunyuan-a13b-instruct",
"slug": "tencent/hunyuan-a13b-instruct",
"name": "Hunyuan A13B Instruct",
"vendor": "Tencent",
"origin": {
"country": "China",
"country_code": "CN",
"flag": "🇨🇳",
"region": "china",
"region_label": "China",
"eu": false
},
"description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...",
"created": 1751987664,
"created_human": "8 jul 2025",
"knowledge_cutoff": "2025-03-31",
"context_length": 131072,
"context_human": "131K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": true
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.14,
"completion_per_1m": 0.57,
"blended_per_1m": 0.2475,
"currency": "USD"
},
"cost_tier": {
"level": 1,
"label": "Zeer laag",
"color": "success",
"detail": "±$0.25 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [
"reasoning",
"budget"
],
"openrouter_url": "https://openrouter.ai/tencent/hunyuan-a13b-instruct",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "morph/morph-v3-large",
"slug": "morph/morph-v3-large",
"name": "Morph V3 Large",
"vendor": "Morph",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: {instruction} {…",
"created": 1751910858,
"created_human": "7 jul 2025",
"knowledge_cutoff": null,
"context_length": 262144,
"context_human": "262K tokens",
"capabilities": {
"text": true,
"vision": false,
"audio": false,
"video": false,
"files": false,
"image_gen": false,
"audio_gen": false,
"reasoning": false
},
"is_free": false,
"pricing": {
"prompt_per_1m": 0.9,
"completion_per_1m": 1.9,
"blended_per_1m": 1.15,
"currency": "USD"
},
"cost_tier": {
"level": 2,
"label": "Laag",
"color": "success",
"detail": "±$1.2 per 1M tokens"
},
"speed": 3,
"speed_source": "estimated",
"performance": {
"tokens_per_sec": null,
"ttft_seconds": null
},
"benchmarks": {
"intelligence_index": null,
"coding_index": null,
"math_index": null,
"agentic_index": null,
"mmlu_pro": null,
"gpqa": null,
"hle": null,
"livecodebench": null,
"scicode": null,
"aime": null,
"ifbench": null,
"tau2": null,
"terminalbench": null,
"design_arena": {
"overall_elo": null,
"code_elo": null,
"count": 0,
"top": []
},
"lmarena": null
},
"scores": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"overall": 0
},
"stars": {
"intelligence": 0,
"coding": 0,
"writing": 0,
"agentic": 0,
"speed": 3
},
"popularity": 7,
"data_sources": [
"openrouter"
],
"use_cases": [
"Algemeen gebruik"
],
"categories": [],
"openrouter_url": "https://openrouter.ai/morph/morph-v3-large",
"available": true,
"tier": {
"key": "lichtgewicht",
"label": "Lichtgewicht",
"sublabel": "snel & goedkoop",
"icon": "bolt",
"desc": "Supersnel en zeer goedkoop. Ideaal voor eenvoudige taken op grote schaal, zoals chat en korte teksten.",
"basis": "inschatting"
},
"value": null,
"curated": false,
"pop_rank": null
},
{
"id": "morph/morph-v3-fast",
"slug": "morph/morph-v3-fast",
"name": "Morph V3 Fast",
"vendor": "Morph",
"origin": {
"country": "Verenigde Staten",
"country_code": "US",
"flag": "🇺🇸",
"region": "north_america",
"region_label": "Verenigde Staten & Canada",
"eu": false
},
"description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code}