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 |
|---|---|---|---|---|---|---|---|---|
| VoyageAI by MongoDB: voyage-code-4mongodb/voyage-code-4 | 13.08.2026 | — | — | — | $0.120 | $0 | 32,000 | 0 evaluations |
| Qwen3 Reranker 8Bqwen/qwen3-reranker-8b | 13.08.2026 | — | — | — | see source | see source | 40,960 | 0 evaluations |
| Qwen: Qwen3 ASR 1.7Bqwen/qwen3-asr-1.7b | 13.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Qwen: Qwen3 ASR 0.6Bqwen/qwen3-asr-0.6b | 13.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| ByteDance Seed: Seedream 5.0 Probytedance-seed/seedream-5-0-pro | 12.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Deepgram: Flux TTSdeepgram/flux-tts | 12.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| ByteDance: Seedance 2.0 Minibytedance/seedance-2.0-mini | 12.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| ByteDance Seed: Seed 2.1 Turbobytedance-seed/seed-2-1-turbo | 12.08.2026 | — | — | — | $0.500 | $2.5 | 262,144 | 0 evaluations |
| Qwen: Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b | 12.08.2026 | — | 71.9AA — next 20% of the cohort | 50.1SS — top 10% of the cohort | $2 | $6 | 1,048,576 | 2 evaluations |
| DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | 12.08.2026 | 23.1CC — below the B band | 68.8AA — next 20% of the cohort | 41.3AA — next 20% of the cohort | $0.111 | $4.44 | 1,048,576 | 3 evaluations |
| SpaceXAI: Grok 4.6x-ai/grok-4.6 | 12.08.2026 | 31BB — next 30% of the cohort | 75.9SS — top 10% of the cohort | 52.5SS — top 10% of the cohort | $2 | $6 | 500,000 | 23 evaluations |
| SpaceXAI: Grok 4.6 (batch)x-ai/grok-4.6:batch | 12.08.2026 | 31BB — next 30% of the cohort | 75.9SS — top 10% of the cohort | 52.5SS — top 10% of the cohort | $1.6 | $4.8 | 500,000 | 23 evaluations |
| xAI: Grok Imagine Image 2.0x-ai/grok-imagine-image-2.0 | 11.08.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| LiquidAI: LFM2.5-2.6Bliquid/lfm-2.5-2.6b | 11.08.2026 | — | 7.7CC — below the B band | — | $0.350 | $0.500 | 128,000 | 1 evaluation |
| LiquidAI: LFM2.5-2.6B (free)liquid/lfm-2.5-2.6b:free | 11.08.2026 | — | 7.7CC — below the B band | — | $0 | $0 | 65,536 | 1 evaluation |
| NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | 11.08.2026 | 5.5CC — below the B band | 26.8CC — below the B band | 3.5CC — below the B band | $0.070 | $0.200 | 262,144 | 3 evaluations |
| NVIDIA: Nemotron 3.5 Lightning (free)nvidia/nemotron-3.5-lightning:free | 11.08.2026 | 5.5CC — below the B band | 26.8CC — below the B band | 3.5CC — below the B band | $0 | $0 | 1,000,000 | 3 evaluations |
| Sakana: Sakana Namazusakana/sakana-namazu | 11.08.2026 | — | — | — | $0.950 | $4 | 262,144 | 0 evaluations |
| Upstage: Solar Pro 4upstage/solar-pro4 | 10.08.2026 | 28.2BB — next 30% of the cohort | 52.7BB — next 30% of the cohort | — | $0.150 | $0.600 | 524,288 | 9 evaluations |
| Meta: Muse Glimmer 30Bmeta/muse-glimmer-30b | 09.08.2026 | 6.3CC — below the B band | 49BB — next 30% of the cohort | 8.5BB — next 30% of the cohort | $0.300 | $1.2 | 131,072 | 8 evaluations |
| Meta: Muse Glimmer 30B (batch)meta/muse-glimmer-30b:batch | 09.08.2026 | 6.3CC — below the B band | 49BB — next 30% of the cohort | 8.5BB — next 30% of the cohort | $0.240 | $0.960 | 131,072 | 8 evaluations |
| ByteDance: Seedance 2.5bytedance/seedance-2.5 | 07.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| inclusionAI: Ling 3.0 Tinyinclusionai/ling-3.0-tiny | 06.08.2026 | — | 26.5CC — below the B band | 4.4CC — below the B band | $0.015 | $0.045 | 262,144 | 2 evaluations |
| OpenAI: GPT Transcribeopenai/gpt-transcribe | 05.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Meta: Muse Spark 1.2meta/muse-spark-1.2 | 05.08.2026 | — | 72.2AA — next 20% of the cohort | 43.2AA — next 20% of the cohort | $1.25 | $4.25 | 1,048,576 | 21 evaluations |
| Qwen: Qwen Image 3qwen/qwen-image-3 | 05.08.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Qwen: Qwen Image 3 Proqwen/qwen-image-3-pro | 05.08.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Black Forest Labs: FLUX 3 Videoblack-forest-labs/flux-3-video | 04.08.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | 31.07.2026 | — | 69.1AA — next 20% of the cohort | 41AA — next 20% of the cohort | $0.043 | $0.300 | 1,048,576 | 10 evaluations |
| DeepSeek: DeepSeek V4 Flash 0731 (batch)deepseek/deepseek-v4-flash-0731:batch | 31.07.2026 | — | 69.1AA — next 20% of the cohort | 41AA — next 20% of the cohort | $0.048 | $0.144 | 1,048,576 | 10 evaluations |
| Thinking Machines: Inkling Smallthinkingmachines/inkling-small | 30.07.2026 | 12.9CC — below the B band | 52.9BB — next 30% of the cohort | 23.5BB — next 30% of the cohort | $0.450 | $1.2 | 524,288 | 3 evaluations |
| Thinking Machines: Inkling Small (batch)thinkingmachines/inkling-small:batch | 30.07.2026 | 12.9CC — below the B band | 52.9BB — next 30% of the cohort | 23.5BB — next 30% of the cohort | $0.360 | $0.960 | 524,288 | 3 evaluations |
| MiniMax: H3minimax/hailuo-3 | 29.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Fish Audio: Transcribe 1fish-audio/transcribe-1 | 29.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Fish Audio: S1fish-audio/s1 | 29.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Fish Audio: S2 Profish-audio/s2-pro | 29.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Fish Audio: S2.1 Pro Free (free)fish-audio/s2.1-pro-free:free | 29.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Fish Audio: S2.1 Profish-audio/s2.1-pro | 29.07.2026 | — | — | — | see source | see source | 0 | 1 evaluation |
| Runway: Aleph 2.0runway/aleph-2 | 29.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Runway: Gen-4.5runway/gen-4.5 | 29.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Qwen: Qwen3.7 Flashqwen/qwen3.7-flash | 27.07.2026 | — | — | — | $0.030 | $0.130 | 1,000,000 | 0 evaluations |
| VoyageAI by MongoDB: rerank-2.5-litemongodb/rerank-2.5-lite | 27.07.2026 | — | — | — | see source | see source | 32,000 | 0 evaluations |
| VoyageAI by MongoDB: rerank-2.5mongodb/rerank-2.5 | 27.07.2026 | — | — | — | see source | see source | 32,000 | 0 evaluations |
| VoyageAI by MongoDB: voyage-multimodal-3.5mongodb/voyage-multimodal-3.5 | 27.07.2026 | — | — | — | $0.120 | $0 | 32,000 | 0 evaluations |
| VoyageAI by MongoDB: voyage-4-litemongodb/voyage-4-lite | 27.07.2026 | — | — | — | $0.020 | $0 | 32,000 | 0 evaluations |
| VoyageAI by MongoDB: voyage-4mongodb/voyage-4 | 27.07.2026 | — | — | — | $0.060 | $0 | 32,000 | 0 evaluations |
| VoyageAI by MongoDB: voyage-4-largemongodb/voyage-4-large | 27.07.2026 | — | — | — | $0.120 | $0 | 32,000 | 0 evaluations |
| Anthropic: Claude Opus 5anthropic/claude-opus-5 | 24.07.2026 | 44.2AA — next 20% of the cohort | 78SS — top 10% of the cohort | 56.5SS — top 10% of the cohort | $5 | $25 | 1,000,000 | 22 evaluations |
| Anthropic: Claude Opus 5 (batch)anthropic/claude-opus-5:batch | 24.07.2026 | 44.2AA — next 20% of the cohort | 78SS — top 10% of the cohort | 56.5SS — top 10% of the cohort | $2.5 | $12.5 | 1,000,000 | 22 evaluations |
| Microsoft AI: MAI-Image-2.5 Promicrosoft/mai-image-2.5-pro | 23.07.2026 | — | — | — | see source | see source | 4,096 | 0 evaluations |
Showing 251–300 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.