Model catalog
Every model listed by OpenRouter's public catalog, with the evaluations the source actually supplies. Grades are our own relative classification inside each benchmark — they are not scores assigned by OpenRouter or the benchmark authors.
Catalog refreshed 13.11.2026 — This snapshot is older than two refresh intervals.
| Model | Added | Intelligence | Coding | Agents | Price in /1M | Price out /1M | Context | Evaluations |
|---|---|---|---|---|---|---|---|---|
| Google: Nano Banana Pro (Gemini 3 Pro Image)google/gemini-3-pro-image | 18.06.2026 | — | — | — | see source | see source | 131,072 | 0 evaluations |
| Cohere: North Mini Code (free)cohere/north-mini-code:free | 17.06.2026 | 3.4CC — below the B band | 36.5CC — below the B band | 1.1CC — below the B band | $0 | $0 | 256,000 | 3 evaluations |
| Z.ai: GLM 5.2z-ai/glm-5.2 | 16.06.2026 | — | 68.8AA — next 20% of the cohort | 38.4AA — next 20% of the cohort | $0.0070 | $6.8 | 1,048,576 | 21 evaluations |
| Z.ai: GLM 5.2 (batch)z-ai/glm-5.2:batch | 16.06.2026 | — | 68.8AA — next 20% of the cohort | 38.4AA — next 20% of the cohort | $0.298 | $0.916 | 1,048,576 | 21 evaluations |
| OpenRouter: Fusionopenrouter/fusion | 13.06.2026 | — | — | — | see source | see source | 1,000,000 | 0 evaluations |
| MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code | 12.06.2026 | — | 60.8BB — next 30% of the cohort | 21BB — next 30% of the cohort | $0.600 | $3.5 | 262,144 | 18 evaluations |
| NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)nvidia/llama-nemotron-rerank-vl-1b-v2:free | 09.06.2026 | — | — | — | see source | see source | 10,240 | 0 evaluations |
| Anthropic: Claude Fable 5anthropic/claude-fable-5 | 09.06.2026 | — | 76.5SS — top 10% of the cohort | 50.7SS — top 10% of the cohort | $10 | $50 | 1,000,000 | 20 evaluations |
| Anthropic: Claude Fable 5 (batch)anthropic/claude-fable-5:batch | 09.06.2026 | — | 76.5SS — top 10% of the cohort | 50.7SS — top 10% of the cohort | $5 | $25 | 1,000,000 | 20 evaluations |
| Sourceful: Riverflow V2.5 Prosourceful/riverflow-v2.5-pro | 04.06.2026 | — | — | — | see source | see source | 32,768 | 4 evaluations |
| Sourceful: Riverflow V2.5 Fastsourceful/riverflow-v2.5-fast | 04.06.2026 | — | — | — | see source | see source | 32,768 | 0 evaluations |
| NVIDIA: Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety | 04.06.2026 | — | — | — | $0.200 | $0.200 | 131,072 | 0 evaluations |
| NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | 04.06.2026 | 11.8CC — below the B band | 49.3BB — next 30% of the cohort | 20.1BB — next 30% of the cohort | $0.600 | $2.4 | 262,144 | 11 evaluations |
| NVIDIA: Nemotron 3 Ultra (free)nvidia/nemotron-3-ultra-550b-a55b:free | 04.06.2026 | 11.8CC — below the B band | 49.3BB — next 30% of the cohort | 20.1BB — next 30% of the cohort | $0 | $0 | 1,000,000 | 11 evaluations |
| Qwen: Qwen3.7 Plusqwen/qwen3.7-plus | 03.06.2026 | — | 55.9BB — next 30% of the cohort | 17.5BB — next 30% of the cohort | $0.320 | $1.28 | 1,000,000 | 10 evaluations |
| Qwen: Qwen3.7 Plus (batch)qwen/qwen3.7-plus:batch | 03.06.2026 | — | 55.9BB — next 30% of the cohort | 17.5BB — next 30% of the cohort | $0.230 | $0.920 | 262,144 | 10 evaluations |
| Microsoft AI: MAI-Voice-2microsoft/mai-voice-2 | 02.06.2026 | — | — | — | see source | see source | 0 | 2 evaluations |
| Microsoft AI: MAI-Transcribe 1.5microsoft/mai-transcribe-1.5 | 02.06.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Microsoft AI: MAI-Image-2.5microsoft/mai-image-2.5 | 02.06.2026 | — | — | — | see source | see source | 4,096 | 4 evaluations |
| MiniMax: MiniMax M3minimax/minimax-m3 | 31.05.2026 | 18.9CC — below the B band | 58.6BB — next 30% of the cohort | 29.5AA — next 20% of the cohort | $0.300 | $1.2 | 1,048,576 | 22 evaluations |
| MiniMax: MiniMax M3 (batch)minimax/minimax-m3:batch | 31.05.2026 | 18.9CC — below the B band | 58.6BB — next 30% of the cohort | 29.5AA — next 20% of the cohort | $0.224 | $0.880 | 524,288 | 22 evaluations |
| StepFun: Step 3.7 Flashstepfun/step-3.7-flash | 28.05.2026 | — | 39.6CC — below the B band | — | $0.200 | $1.15 | 262,144 | 9 evaluations |
| Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8 | 27.05.2026 | — | 74.3AA — next 20% of the cohort | 41.9AA — next 20% of the cohort | $5 | $25 | 1,000,000 | 27 evaluations |
| Anthropic: Claude Opus 4.8 (batch)anthropic/claude-opus-4.8:batch | 27.05.2026 | — | 74.3AA — next 20% of the cohort | 41.9AA — next 20% of the cohort | $2.5 | $12.5 | 1,000,000 | 27 evaluations |
| NVIDIA: Parakeet TDT 0.6B v3nvidia/parakeet-tdt-0.6b-v3 | 27.05.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Qwen: Qwen3.7 Maxqwen/qwen3.7-max | 21.05.2026 | — | 66AA — next 20% of the cohort | 22.5BB — next 30% of the cohort | $1.48 | $4.43 | 1,000,000 | 21 evaluations |
| SpaceXAI: Grok Build 0.1x-ai/grok-build-0.1 | 20.05.2026 | — | 51.5BB — next 30% of the cohort | — | $1 | $2 | 256,000 | 1 evaluation |
| Google: Gemini Embedding 2google/gemini-embedding-2 | 20.05.2026 | — | — | — | $0.200 | $0 | 8,192 | 0 evaluations |
| Google: Gemini Embedding 2 (batch)google/gemini-embedding-2:batch | 20.05.2026 | — | — | — | $0.100 | $0 | 8,192 | 0 evaluations |
| Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash | 19.05.2026 | — | 70.1AA — next 20% of the cohort | 26BB — next 30% of the cohort | $1.5 | $9 | 1,048,576 | 27 evaluations |
| Google: Gemini 3.5 Flash (batch)google/gemini-3.5-flash:batch | 19.05.2026 | — | 70.1AA — next 20% of the cohort | 26BB — next 30% of the cohort | $0.750 | $4.5 | 1,048,576 | 27 evaluations |
| SpaceXAI: Grok Imagine Videox-ai/grok-imagine-video | 18.05.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Mistral: Voxtral Mini Transcribemistralai/voxtral-mini-transcribe | 15.05.2026 | — | — | — | see source | see source | 16,384 | 0 evaluations |
| SpaceXAI: Grok Voice TTS 1.0x-ai/grok-voice-tts-1.0 | 15.05.2026 | — | — | — | see source | see source | 15,000 | 0 evaluations |
| Recraft: Recraft V4.1 Pro Vectorrecraft/recraft-v4.1-pro-vector | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4.1 Vectorrecraft/recraft-v4.1-vector | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4.1 Utility Prorecraft/recraft-v4.1-utility-pro | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4.1 Utilityrecraft/recraft-v4.1-utility | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4.1 Prorecraft/recraft-v4.1-pro | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4.1recraft/recraft-v4.1 | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4 Pro Vectorrecraft/recraft-v4-pro-vector | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4 Vectorrecraft/recraft-v4-vector | 13.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Perceptron: Perceptron Mk1perceptron/perceptron-mk1 | 12.05.2026 | — | — | — | $0.150 | $1.5 | 32,768 | 0 evaluations |
| Recraft: Recraft V4 Prorecraft/recraft-v4-pro | 07.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V4recraft/recraft-v4 | 07.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Recraft: Recraft V3recraft/recraft-v3 | 07.05.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite | 07.05.2026 | — | — | — | $0.250 | $1.5 | 1,048,576 | 0 evaluations |
| Google: Gemini 3.1 Flash Lite (batch)google/gemini-3.1-flash-lite:batch | 07.05.2026 | — | — | — | $0.125 | $0.750 | 1,048,576 | 0 evaluations |
| OpenAI: GPT Chat Latestopenai/gpt-chat-latest | 05.05.2026 | — | — | — | $5 | $30 | 400,000 | 0 evaluations |
| Google: Chirp 3google/chirp-3 | 05.05.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
Showing 351–400 of 703 models
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.