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 |
|---|---|---|---|---|---|---|---|---|
| Microsoft AI: MAI-Voice-2-Flashmicrosoft/mai-voice-2-flash | 23.07.2026 | — | — | — | see source | see source | 0 | 2 evaluations |
| inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash | 23.07.2026 | — | 50.6BB — next 30% of the cohort | 19.3BB — next 30% of the cohort | $0.021 | $0.063 | 262,144 | 2 evaluations |
| Qwen: Qwen-Audio-3.0-TTS Flashqwen/qwen-audio-3.0-tts-flash | 23.07.2026 | — | — | — | see source | see source | 0 | 1 evaluation |
| Qwen: Qwen-Audio-3.0-TTS Plusqwen/qwen-audio-3.0-tts-plus | 23.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| SpaceXAI: Grok STT 1.0x-ai/grok-stt-1.0 | 23.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Google: Gemini 3.6 Flashgoogle/gemini-3.6-flash | 21.07.2026 | — | 69.2AA — next 20% of the cohort | 29BB — next 30% of the cohort | $0.750 | $3.75 | 1,048,576 | 20 evaluations |
| Google: Gemini 3.6 Flash (batch)google/gemini-3.6-flash:batch | 21.07.2026 | — | 69.2AA — next 20% of the cohort | 29BB — next 30% of the cohort | $0.375 | $1.88 | 1,048,576 | 20 evaluations |
| Google: Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | 21.07.2026 | 11.7CC — below the B band | 49.3BB — next 30% of the cohort | 14.3BB — next 30% of the cohort | $0.300 | $2.5 | 1,048,576 | 3 evaluations |
| Google: Gemini 3.5 Flash Lite (batch)google/gemini-3.5-flash-lite:batch | 21.07.2026 | 11.7CC — below the B band | 49.3BB — next 30% of the cohort | 14.3BB — next 30% of the cohort | $0.150 | $1.25 | 1,048,576 | 3 evaluations |
| Krea: Krea 2 Largekrea/krea-2-large | 20.07.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Krea: Krea 2 Mediumkrea/krea-2-medium | 20.07.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Krea: Krea 2 Medium Turbokrea/krea-2-medium-turbo | 20.07.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Meituan: LongCat 2.0meituan/longcat-2.0 | 20.07.2026 | — | 45.3BB — next 30% of the cohort | 14BB — next 30% of the cohort | $0.300 | $1.2 | 1,048,756 | 2 evaluations |
| SpaceXAI: Grok Imagine Video 1.5x-ai/grok-imagine-video-1.5 | 20.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Thinking Machines: Inklingthinkingmachines/inkling | 17.07.2026 | 12.5CC — below the B band | 52.1BB — next 30% of the cohort | 22.5BB — next 30% of the cohort | $1 | $4.05 | 524,288 | 12 evaluations |
| Auto Router (Beta)openrouter/auto-beta | 17.07.2026 | — | — | — | see source | see source | 2,000,000 | 0 evaluations |
| Deepgram: Aura-2deepgram/aura-2 | 16.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| MoonshotAI: Kimi K3moonshotai/kimi-k3 | 16.07.2026 | 17.4CC — below the B band | 72AA — next 20% of the cohort | 29.3AA — next 20% of the cohort | $0.192 | $16 | 1,048,576 | 22 evaluations |
| MoonshotAI: Kimi K3 (batch)moonshotai/kimi-k3:batch | 16.07.2026 | 17.4CC — below the B band | 72AA — next 20% of the cohort | 29.3AA — next 20% of the cohort | $2.28 | $11.4 | 1,048,576 | 22 evaluations |
| Meta: Muse Spark 1.1meta/muse-spark-1.1 | 16.07.2026 | — | 71.3AA — next 20% of the cohort | 25.8BB — next 30% of the cohort | $1.25 | $4.25 | 1,048,576 | 22 evaluations |
| NVIDIA: Nemotron 3 Embed 1B (free)nvidia/nemotron-3-embed-1b:free | 16.07.2026 | — | — | — | $0 | $0 | 32,768 | 0 evaluations |
| MiniMax: Speech 2.8 HDminimax/speech-2.8-hd | 16.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| MiniMax: Speech 2.8 Turbominimax/speech-2.8-turbo | 16.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Deepgram: Nova-3deepgram/nova-3 | 15.07.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro | 09.07.2026 | — | — | — | $0.200 | $1.2 | 1,050,000 | 0 evaluations |
| OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batch | 09.07.2026 | — | — | — | $0.100 | $0.600 | 1,050,000 | 0 evaluations |
| OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-luna | 09.07.2026 | 23.8BB — next 30% of the cohort | 71.4AA — next 20% of the cohort | 42.1AA — next 20% of the cohort | $0.200 | $1.2 | 1,050,000 | 3 evaluations |
| OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batch | 09.07.2026 | 23.8BB — next 30% of the cohort | 71.4AA — next 20% of the cohort | 42.1AA — next 20% of the cohort | $0.100 | $0.600 | 1,050,000 | 3 evaluations |
| OpenAI: GPT-5.6 Terra Proopenai/gpt-5.6-terra-pro | 09.07.2026 | — | — | — | $2 | $12 | 1,050,000 | 0 evaluations |
| OpenAI: GPT-5.6 Terra Pro (batch)openai/gpt-5.6-terra-pro:batch | 09.07.2026 | — | — | — | $1 | $6 | 1,050,000 | 0 evaluations |
| OpenAI: GPT-5.6 Terraopenai/gpt-5.6-terra | 09.07.2026 | 32.3BB — next 30% of the cohort | 76.7SS — top 10% of the cohort | 43.2AA — next 20% of the cohort | $2 | $12 | 1,050,000 | 3 evaluations |
| OpenAI: GPT-5.6 Terra (batch)openai/gpt-5.6-terra:batch | 09.07.2026 | 32.3BB — next 30% of the cohort | 76.7SS — top 10% of the cohort | 43.2AA — next 20% of the cohort | $1 | $6 | 1,050,000 | 3 evaluations |
| OpenAI: GPT-5.6 Sol Proopenai/gpt-5.6-sol-pro | 09.07.2026 | — | — | — | $4 | $20 | 1,050,000 | 0 evaluations |
| OpenAI: GPT-5.6 Sol Pro (batch)openai/gpt-5.6-sol-pro:batch | 09.07.2026 | — | — | — | $2 | $10 | 1,050,000 | 0 evaluations |
| OpenAI: GPT-5.6 Solopenai/gpt-5.6-sol | 09.07.2026 | — | 78.3SS — top 10% of the cohort | 47.4AA — next 20% of the cohort | $4.4 | $22 | 1,050,000 | 2 evaluations |
| OpenAI: GPT-5.6 Sol (batch)openai/gpt-5.6-sol:batch | 09.07.2026 | — | 78.3SS — top 10% of the cohort | 47.4AA — next 20% of the cohort | $2 | $10 | 1,050,000 | 2 evaluations |
| SpaceXAI: Grok 4.5x-ai/grok-4.5 | 08.07.2026 | — | 72.4AA — next 20% of the cohort | 41.2AA — next 20% of the cohort | $2 | $6 | 500,000 | 22 evaluations |
| AionLabs: Aion-3.0-Miniaion-labs/aion-3.0-mini | 07.07.2026 | — | — | — | $0.700 | $1.4 | 131,072 | 0 evaluations |
| AionLabs: Aion-3.0aion-labs/aion-3.0 | 07.07.2026 | — | — | — | $3 | $6 | 131,072 | 0 evaluations |
| Tencent: Hy3tencent/hy3 | 06.07.2026 | — | — | — | $0.132 | $0.528 | 262,144 | 6 evaluations |
| Anthropic: Claude Sonnet 5anthropic/claude-sonnet-5 | 30.06.2026 | — | 71.5AA — next 20% of the cohort | 43.6AA — next 20% of the cohort | $2 | $10 | 1,000,000 | 22 evaluations |
| Anthropic: Claude Sonnet 5 (batch)anthropic/claude-sonnet-5:batch | 30.06.2026 | — | 71.5AA — next 20% of the cohort | 43.6AA — next 20% of the cohort | $1 | $5 | 1,000,000 | 22 evaluations |
| Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-image | 30.06.2026 | — | — | — | see source | see source | 65,536 | 0 evaluations |
| Sakana: Fugu Ultrasakana/fugu-ultra | 24.06.2026 | — | — | — | $5 | $30 | 1,000,000 | 0 evaluations |
| Alibaba: HappyHorse 1.1alibaba/happyhorse-1.1 | 24.06.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| OpenAI: GPT Image 2openai/gpt-image-2 | 24.06.2026 | — | — | — | see source | see source | 400,000 | 0 evaluations |
| OpenAI: GPT Image 1openai/gpt-image-1 | 24.06.2026 | — | — | — | see source | see source | 400,000 | 1 evaluation |
| OpenAI: GPT Image 1 Miniopenai/gpt-image-1-mini | 24.06.2026 | — | — | — | see source | see source | 400,000 | 0 evaluations |
| Alibaba: HappyHorse 1.0alibaba/happyhorse-1.0 | 24.06.2026 | — | — | — | see source | see source | 0 | 0 evaluations |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image)google/gemini-3.1-flash-image | 18.06.2026 | — | — | — | see source | see source | 131,072 | 0 evaluations |
Showing 301–350 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.