MODELS
Explore model versions
Search canonical identities and compare access and capability data.
431 of 431 model versions
| Model | Organization | Family | Providers | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Official price | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 Max alibaba/qwen/qwen3-8-max | Alibaba | Qwen | 3 | 1M | 131K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-08-03 | 2026-08-03 | |
| DeepSeek V4 Flash 0731 deepseek/deepseek/v4-flash-0731 | DeepSeek | DeepSeek | 6 | 1M | 66K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-07-31 | 2026-07-31 | |
| Inkling Small thinkingmachines/ling/inkling-small | TMThinking Machines | Ling | 4 | 1M | 1M | TextImageAudio | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-07-30 | 2026-07-30 | |
| Qwen3.7 Flash alibaba/qwen/qwen3-7-flash | Alibaba | Qwen | 3 | 1M | 66K | TextImageVideo | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2026-07-27 | 2026-07-15 | |
| Claude Opus 5 anthropic/claude/opus-5 | Anthropic | Claude | 14 | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | -No | Closed | input $5/M · cache read $0.5/M output $25/M · cache write $6.25/M | 2026-07-24 | 2026-07-24 | |
| Claude Opus 5 (Fast) anthropic/claude/opus-5-fast | Anthropic | Claude | 3 | 1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2026-07-24 | 2026-07-24 | |
| Ling-3.0-flash (free) inclusionai/ling/3-0-flash-free | Inclusionai | Ling | 2 | 262K | 33K | Text | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2026-07-23 | 2026-07-23 | |
| Gemini 3.5 Flash Lite google/gemini/3-5-flash-lite | Gemini | 10 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $0.3/M · cache read $0.03/M output $2.5/M | 2026-07-21 | 2026-07-21 | ||
| Gemini 3.6 Flash google/gemini/3-6-flash | Gemini | 10 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $1.5/M · cache read $0.15/M output $7.5/M | 2026-07-21 | 2026-07-21 | ||
| Laguna S 2.1 poolside/laguna/s-2-1 | POPoolside | Laguna | 5 | 1M | 33K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0/M · cache read $0/M output $0/M · cache write $0/M | 2026-07-21 | 2026-07-21 | |
| Qwen3.8 Max Preview alibaba/qwen/qwen3-8-max-preview | Alibaba | Qwen | 2 | 1M | 131K | TextImageVideo | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2026-07-19 | 2026-07-19 | |
| Kimi K3 moonshotai/kimi/k3 | Moonshot AI | Kimi | 30 | 1M | 131K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $3/M · cache read $0.3/M output $15/M | 2026-07-16 | 2026-07-30 | |
| Inkling thinkingmachines/ling/inkling | TMThinking Machines | Ling | 11 | 1M | 1M | TextImageAudio | Text | Yes | Yes | -No | Yes | Open weight | input $1.87/M · cache read $0.374/M output $4.68/M | 2026-07-15 | 2026-07-17 | |
| KAT-Coder-Air V2.5 kwaipilot/kat/coder-air-v2-5 | Kwaipilot | Kat | 4 | 256K | 80K | Text | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-07-10 | 2026-07-14 | |
| KAT-Coder-Pro V2.5 kwaipilot/kat/coder-pro-v2-5 | Kwaipilot | Kat | 4 | 256K | 80K | Text | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-07-10 | 2026-07-14 | |
| GPT-5.6 Luna openai/gpt/5-6-luna | OpenAI | GPT | 22 | 1.1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $0.2/M · cache read $0.02/M output $1.2/M · cache write $0.25/M | 2026-07-09 | 2026-07-09 | |
| GPT-5.6 Sol openai/gpt/5-6-sol | OpenAI | GPT | 22 | 1.1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $5/M · cache read $0.5/M output $30/M · cache write $6.25/M | 2026-07-09 | 2026-07-09 | |
| GPT-5.6 Terra openai/gpt/5-6-terra | OpenAI | GPT | 22 | 1.1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $2/M · cache read $0.2/M output $12/M · cache write $2.5/M | 2026-07-09 | 2026-07-09 | |
| GPT-5.6 Luna Pro openai/gpt/5-6-luna-pro | OpenAI | GPT | 3 | 1.1M | 128K | DocumentImageText | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2026-07-09 | 2026-07-09 | |
| GPT-5.6 Terra Pro openai/gpt/5-6-terra-pro | OpenAI | GPT | 3 | 1.1M | 128K | DocumentImageText | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2026-07-09 | 2026-07-09 | |
| GPT-5.6 Sol Pro openai/gpt/5-6-sol-pro | OpenAI | GPT | 3 | 1.1M | 128K | DocumentImageText | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2026-07-09 | 2026-07-09 | |
| Grok 4.5 xai/grok/4-5 | xAI | Grok | 16 | 500K | 500K | TextImageDocument | Text | Yes | Yes | Yes | Yes | Closed | input $2/M · cache read $0.3/M output $6/M | 2026-07-08 | 2026-07-08 | |
| Aion-3.0-Mini aion-labs/aion/3-0-mini | Aion Labs | Aion | 3 | 131K | 33K | Text | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2026-07-07 | 2026-07-07 | |
| Aion-3.0 aion-labs/aion/3-0 | Aion Labs | Aion | 3 | 131K | 33K | Text | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2026-07-07 | 2026-07-07 | |
| GPT-Realtime-2.1 openai/gpt/realtime-2-1 | OpenAI | GPT | 2 | 128K | 32K | TextAudioImage | TextAudio | Yes | Yes | -No | -No | Closed | input $4/M · cache read $0.4/M output $24/M | 2026-07-06 | 2026-07-06 | |
| Hy3 tencent/hy/hy3 | Tencent | Hy | 11 | 256K | 64K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-07-06 | 2026-07-06 | |
| Laguna XS 2.1 poolside/laguna/xs-2-1 | POPoolside | Laguna | 4 | 262K | 33K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0/M · cache read $0/M output $0/M · cache write $0/M | 2026-07-02 | 2026-07-02 | |
| Claude Sonnet 5 anthropic/claude/sonnet-5 | Anthropic | Claude | 20 | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | -No | Closed | input $2/M · cache read $0.2/M output $10/M · cache write $2.5/M | 2026-06-30 | 2026-07-01 | |
| Nano Banana 2 Lite google/gemini/3-1-flash-lite-image | Gemini | 4 | 66K | 4.1K | TextImage | TextImage | Yes | Yes | -No | Yes | Closed | input $0.25/M output $30/M | 2026-06-30 | 2026-06-30 | ||
| Gemini Omni Flash Preview google/gemini/omni-flash-preview | Gemini | 2 | 1M | 58K | TextImageVideo | Video | Yes | -No | -No | -No | Closed | input $1.5/M output $17.5/M | 2026-06-30 | 2026-06-30 | ||
| LongCat-2.0 meituan/longcat/2-0 | MEMeituan | Longcat | 3 | 1M | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-06-30 | 2026-07-20 | |
| Ornith 1.0 31B deepreinforce/ornith/1-0-31b | DEDeepReinforce | Ornith | - | 262K | - | TextImage | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-06-25 | 2026-06-25 | |
| Ornith 1.0 35B deepreinforce/ornith/1-0-35b | DEDeepReinforce | Ornith | - | 262K | - | TextImage | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-06-25 | 2026-06-25 | |
| Ornith 1.0 397B deepreinforce/ornith/1-0-397b | DEDeepReinforce | Ornith | - | 262K | - | TextImage | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-06-25 | 2026-06-25 | |
| Ornith 1.0 9B deepreinforce/ornith/1-0-9b | DEDeepReinforce | Ornith | - | 262K | - | TextImage | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-06-25 | 2026-06-25 | |
| Nex-N2-Mini nex-agi/nex/n2-mini | NANex Agi | Nex | 3 | 262K | 262K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-06-24 | 2026-06-24 | |
| North Mini Code (free) cohere/north/mini-code-free | Cohere | North | 2 | 256K | 64K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-06-17 | 2026-06-17 | |
| Fugu sakana/fugu/fugu | SASakana AI | Fugu | 1 | 1M | - | TextImage | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2026-06-15 | 2026-06-15 | |
| Fugu Ultra sakana/fugu/ultra | SASakana AI | Fugu | 7 | 1M | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $5/M · cache read $0.5/M output $30/M | 2026-06-15 | 2026-06-22 | |
| GLM-5.2 zhipuai/glm/5-2 | Zhipu AI | GLM | 36 | 1M | 131K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $1.4/M · cache read $0.26/M output $4.4/M · cache write $0/M | 2026-06-13 | 2026-07-22 | |
| Kimi K2.7 Code moonshotai/kimi/k2-7-code | Moonshot AI | Kimi | 38 | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $0.95/M · cache read $0.19/M output $4/M | 2026-06-12 | 2026-07-22 | |
| Kimi K2.7 Code Highspeed moonshotai/kimi/k2-7-code-highspeed | Moonshot AI | Kimi | 7 | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $1.9/M · cache read $0.38/M output $8/M | 2026-06-12 | 2026-06-12 | |
| Claude Fable 5 anthropic/claude/fable-5 | Anthropic | Claude | 23 | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | -No | Closed | input $10/M · cache read $1/M output $50/M · cache write $12.5/M | 2026-06-09 | 2026-06-11 | |
| North Mini Code cohere/north/mini-code-1-0 | Cohere | North | 1 | 256K | 64K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0/M output $0/M | 2026-06-09 | 2026-06-09 | |
| Gemini 3.5 Live Translate Preview google/gemini/3-5-live-translate-preview | Gemini | 1 | 131K | 66K | Audio | AudioText | -No | -No | -No | -No | Closed | input $3.5/M output $21/M | 2026-06-09 | 2026-06-09 | ||
| MiMo-V2.5-Pro-UltraSpeed xiaomi/mimo/v2-5-pro-ultraspeed | Xiaomi | MiMo | 1 | 1M | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $1.305/M · cache read $0.0108/M output $2.61/M | 2026-06-08 | 2026-06-09 | |
| Nex-N2-Pro nex-agi/nex/n2-pro | NANex Agi | Nex | 3 | 262K | 262K | TextImage | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-06-08 | 2026-06-08 | |
| Nemotron 3 Ultra 550B A55B nvidia/nemotron/3-ultra-550b-a55b | NVIDIA | Nemotron | 8 | 1M | 128K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.5/M · cache read $0.15/M output $2.5/M | 2026-06-04 | 2026-06-04 | |
| Nemotron 3.5 Content Safety nvidia/nemotron/3-5-content-safety | NVIDIA | Nemotron | 2 | 128K | 8.2K | TextImage | Text | Yes | -No | -No | Yes | Open weight | Pricing unavailable | 2026-06-04 | 2026-06-04 | |
| Qwen3.7 Plus alibaba/qwen/qwen3-7-plus | Alibaba | Qwen | 21 | 1M | 64K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | input $0.5/M · cache read $0.05/M output $3/M · cache write $0.625/M | 2026-06-02 | 2026-07-22 | |
| MAI-Code-1-Flash microsoft/mai/code-1-flash | Microsoft | MAI | - | 256K | 128K | Text | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-06-02 | 2026-06-08 | |
| MiniMax-M3 minimax/minimax/m3 | MiniMax | Minimax | 21 | 512K | 128K | TextImageVideo | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.06/M output $1.2/M | 2026-06-01 | 2026-07-31 | |
| Grok Imagine Video 1.5 xai/grok/imagine-video-1-5 | xAI | Grok | 2 | 1K | - | TextImageVideo | Video | -No | -No | -No | -No | Closed | input $0.01/image output $0.08/video second | 2026-05-30 | 2026-05-30 | |
| Step 3.7 Flash stepfun/step/3-7-flash | StepFun | Step | 11 | 256K | 256K | TextImageVideo | Text | Yes | Yes | -No | Yes | Open weight | input $0.185/M · cache read $0.037/M output $1.11/M | 2026-05-29 | 2026-06-29 | |
| Claude Opus 4.8 anthropic/claude/opus-4-8 | Anthropic | Claude | 32 | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | -No | Closed | input $5/M · cache read $0.5/M output $25/M · cache write $6.25/M | 2026-05-28 | 2026-06-11 | |
| Nano Banana Pro google/gemini/3-pro-image | Gemini | 5 | 66K | 33K | TextImage | TextImage | Yes | -No | -No | Yes | Closed | input $2/M output $120/M | 2026-05-28 | 2026-05-28 | ||
| Nano Banana 2 google/gemini/3-1-flash-image | Gemini | 5 | 131K | 33K | TextImageVideoDocument | TextImage | Yes | -No | -No | Yes | Closed | input $0.5/M output $60/M | 2026-05-28 | 2026-05-28 | ||
| Claude Opus 4.8 (Fast) anthropic/claude/opus-4-8-fast | Anthropic | Claude | 3 | 1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2026-05-27 | 2026-05-28 | |
| Qwen3.7 Max alibaba/qwen/qwen3-7-max | Alibaba | Qwen | 21 | 1M | 66K | Text | Text | Yes | Yes | Yes | Yes | Closed | input $2.5/M · cache read $0.5/M output $7.5/M · cache write $3.125/M | 2026-05-21 | 2026-07-22 | |
| Command A Plus cohere/command/a-plus-05-2026 | Cohere | Command | 2 | 128K | 64K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $2.5/M output $10/M | 2026-05-20 | 2026-06-09 | |
| Gemini 3.5 Flash google/gemini/3-5-flash | Gemini | 22 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $1.5/M · cache read $0.15/M output $9/M | 2026-05-19 | 2026-06-11 | ||
| Gemini Flash Latest google/gemini/flash-latest | Gemini | 6 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $1.5/M · cache read $0.15/M output $9/M | 2026-05-19 | 2026-05-19 | ||
| Claude Opus 4.7 (Fast) anthropic/claude/opus-4-7-fast | Anthropic | Claude | 2 | 1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2026-05-12 | 2026-04-16 | |
| Perceptron Mk1 perceptron/perceptron/mk1 | PEPerceptron | Perceptron | 3 | 33K | 8.2K | TextImageVideo | Text | Yes | -No | Yes | Yes | Closed | Pricing unavailable | 2026-05-12 | 2026-05-12 | |
| Ring-2.6-1T inclusionai/ring/2-6-1t | Inclusionai | Ring | 5 | 262K | 66K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-05-08 | 2026-05-27 | |
| Gemini 3.1 Flash Lite google/gemini/3-1-flash-lite | Gemini | 16 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $0.25/M · cache read $0.025/M output $1.5/M | 2026-05-07 | 2026-05-07 | ||
| Gemini Flash-Lite Latest google/gemini/flash-lite-latest | Gemini | 5 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $0.25/M · cache read $0.025/M output $1.5/M | 2026-05-07 | 2026-05-07 | ||
| GPT Realtime Whisper openai/whisper/gpt-realtime-whisper | OpenAI | Whisper | 1 | - | - | Audio | Text | -No | -No | -No | Yes | Closed | Pricing unavailable | 2026-05-07 | 2026-05-07 | |
| GPT-5.5 Instant openai/gpt/5-5-instant | OpenAI | GPT | 1 | 400K | 128K | TextImageDocument | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-05-05 | 2026-05-28 | |
| GPT Chat Latest openai/gpt/chat-latest | OpenAI | GPT | 3 | 400K | 128K | TextImageDocument | Text | -No | Yes | Yes | -No | Closed | Pricing unavailable | 2026-05-05 | 2026-05-05 | |
| Granite 4.1 8B ibm-granite/granite/4-1-8b | Ibm Granite | Granite | 4 | 131K | 131K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-04-30 | 2026-04-30 | |
| Mistral Medium 3.5 mistral/mistral/medium-3-5 | Mistral AI | Mistral | 2 | 262K | - | TextImageDocument | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-04-30 | 2026-04-30 | |
| Mistral Medium 3.5 mistral/mistral/medium-2604 | Mistral AI | Mistral | 1 | 262K | 262K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $1.5/M output $7.5/M | 2026-04-29 | 2026-04-29 | |
| Mistral Medium (latest) mistral/mistral/medium-latest | Mistral AI | Mistral | 2 | 262K | 262K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $1.5/M output $7.5/M | 2026-04-29 | 2026-04-29 | |
| Nemotron 3 Nano Omni 30B A3B Reasoning nvidia/nemotron/3-nano-omni-30b-a3b-reasoning | NVIDIA | Nemotron | 5 | 256K | 66K | TextImageVideoAudio | Text | Yes | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2026-04-28 | 2026-04-28 | |
| Laguna M.1 poolside/laguna/m-1 | POPoolside | Laguna | 3 | 262K | 33K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0/M · cache read $0/M output $0/M · cache write $0/M | 2026-04-28 | 2026-06-13 | |
| Laguna XS.2 poolside/laguna/xs-2 | POPoolside | Laguna | 2 | 262K | 33K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-04-28 | 2026-06-13 | |
| Qwen3.6 Flash alibaba/qwen/qwen3-6-flash | Alibaba | Qwen | 16 | 1M | 66K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | input $0.1875/M output $1.125/M · cache write $0.234375/M | 2026-04-27 | 2026-07-22 | |
| Qwen3.5 Plus 2026-04-20 alibaba/qwen/qwen3-5-plus-20260420 | Alibaba | Qwen | 2 | 1M | 66K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-04-27 | 2026-04-27 | |
| DeepSeek V4 Flash deepseek/deepseek/v4-flash | DeepSeek | DeepSeek | 34 | 1M | 384K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.14/M · cache read $0.0028/M output $0.28/M | 2026-04-24 | 2026-07-31 | |
| DeepSeek V4 Pro deepseek/deepseek/v4-pro | DeepSeek | DeepSeek | 38 | 1M | 384K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.435/M · cache read $0.003625/M output $0.87/M | 2026-04-24 | 2026-07-22 | |
| GPT-5.5 openai/gpt/5-5 | OpenAI | GPT | 35 | 1.1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $5/M · cache read $0.5/M output $30/M | 2026-04-23 | 2026-04-24 | |
| GPT-5.5 Pro openai/gpt/5-5-pro | OpenAI | GPT | 11 | 1.1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $30/M output $180/M | 2026-04-23 | 2026-04-24 | |
| Ling-2.6-1T inclusionai/ling/2-6-1t | Inclusionai | Ling | 4 | 262K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-04-23 | 2026-06-29 | |
| Qwen3.6 27B alibaba/qwen/qwen3-6-27b | Alibaba | Qwen | 13 | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.6/M output $3.6/M | 2026-04-22 | 2026-06-11 | |
| Gemini Embedding 2 google/gemini/embedding-2 | Gemini | 2 | 8.2K | 3.1K | TextImageAudioVideoDocument | Text | -No | -No | -No | -No | Closed | input $0.2/M output $0/M | 2026-04-22 | 2026-04-22 | ||
| MiMo-V2.5 xiaomi/mimo/v2-5 | Xiaomi | MiMo | 15 | 1M | 131K | TextImageAudioVideo | Text | Yes | Yes | -No | Yes | Open weight | input $0.14/M · cache read $0.0028/M output $0.28/M | 2026-04-22 | 2026-06-24 | |
| MiMo-V2.5-Pro xiaomi/mimo/v2-5-pro | Xiaomi | MiMo | 15 | 1M | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.435/M · cache read $0.0036/M output $0.87/M | 2026-04-22 | 2026-06-24 | |
| Deep Research Max Preview google/gemini/deep-research-max-preview-04-2026 | Gemini | 1 | 1M | 66K | TextImageVideoAudioDocument | TextImage | Yes | Yes | -No | -No | Closed | input $2/M · cache read $0.2/M output $12/M | 2026-04-21 | 2026-04-21 | ||
| Gemini Deep Research Preview google/gemini/deep-research-preview-04-2026 | Gemini | 1 | 1M | 66K | TextImageVideoAudioDocument | TextImage | Yes | Yes | -No | -No | Closed | input $2/M · cache read $0.2/M output $12/M | 2026-04-21 | 2026-04-21 | ||
| Kimi K2.6 moonshotai/kimi/k2-6 | Moonshot AI | Kimi | 57 | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Open weight | input $0.95/M · cache read $0.16/M output $4/M | 2026-04-21 | 2026-07-22 | |
| GPT-Image-2 openai/gpt/image-2 | OpenAI | GPT | 6 | - | - | TextImage | Image | -No | -No | -No | -No | Closed | input $5/M · cache read $1.25/M output $30/M | 2026-04-21 | 2026-04-21 | |
| GPT-5.4 Image 2 openai/gpt/5-4-image-2 | OpenAI | GPT | 2 | 272K | 128K | ImageTextDocument | ImageText | Yes | -No | Yes | -No | Closed | Pricing unavailable | 2026-04-21 | 2026-04-21 | |
| Ling-2.6-flash inclusionai/ling/2-6-flash | Inclusionai | Ling | 4 | 262K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-04-21 | 2026-04-24 | |
| Qwen3.6 Max Preview alibaba/qwen/qwen3-6-max-preview | Alibaba | Qwen | 10 | 262K | 66K | Text | Text | Yes | Yes | Yes | Yes | Closed | input $1.3/M · cache read $0.13/M output $7.8/M · cache write $1.625/M | 2026-04-20 | 2026-05-09 | |
| Hy3 preview tencent/hy/hy3-preview | Tencent | Hy | 8 | 256K | 64K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-04-20 | 2026-04-20 | |
| Qwen3.6 35B-A3B alibaba/qwen/qwen3-6-35b-a3b | Alibaba | Qwen | 12 | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.248/M output $1.485/M | 2026-04-17 | 2026-07-22 | |
| Grok 4.3 xai/grok/4-3 | xAI | Grok | 18 | 1M | 30K | TextImageDocument | Text | Yes | Yes | Yes | Yes | Closed | input $1.25/M · cache read $0.2/M output $2.5/M | 2026-04-17 | 2026-06-11 | |
| Claude Opus 4.7 anthropic/claude/opus-4-7 | Anthropic | Claude | 30 | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | -No | Closed | input $5/M · cache read $0.5/M output $25/M · cache write $6.25/M | 2026-04-16 | 2026-06-11 | |
| Nemotron 3 Content Safety nvidia/nemotron/3-content-safety | NVIDIA | Nemotron | 1 | 128K | 4.1K | Text | Text | -No | -No | -No | -No | Open weight | input $0/M output $0/M | 2026-04-16 | 2026-04-16 | |
| Grok Build 0.1 xai/grok-build/0-1 | xAI | Grok Build | 14 | 256K | 256K | TextImageDocument | Text | Yes | Yes | Yes | Yes | Closed | input $1/M · cache read $0.2/M output $2/M | 2026-04-16 | 2026-06-11 | |
| Gemini 3.1 Flash TTS Preview google/gemini/3-1-flash-tts-preview | Gemini | 1 | 8.2K | 16K | Text | Audio | -No | -No | -No | Yes | Closed | input $1/M output $20/M | 2026-04-15 | 2026-04-15 | ||
| Gemini Robotics-ER 1.6 Preview google/gemini/robotics-er-1-6-preview | Gemini | 1 | 131K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Closed | input $1/M output $5/M | 2026-04-14 | 2026-04-14 | ||
| Muse Spark 1.1 meta/muse/spark-1-1 | Meta | Muse | 9 | 1M | 32K | TextImageDocumentVideo | Text | Yes | Yes | Yes | Yes | Closed | input $1.25/M · cache read $0.15/M output $4.25/M | 2026-04-08 | 2026-07-09 | |
| GLM-5.1 zhipuai/glm/5-1 | Zhipu AI | GLM | 29 | 200K | 131K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $1.4/M · cache read $0.26/M output $4.4/M · cache write $0/M | 2026-04-07 | 2026-07-22 | |
| Qwen3.6 Plus alibaba/qwen/qwen3-6-plus | Alibaba | Qwen | 20 | 1M | 66K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | input $0.5/M · cache read $0.05/M output $3/M · cache write $0.625/M | 2026-04-02 | 2026-07-22 | |
| Gemma 4 26B A4B IT google/gemma/4-26b-a4b-it | Gemma | 16 | 262K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0.15/M · cache read $0.015/M output $0.6/M | 2026-04-02 | 2026-07-22 | ||
| Gemma 4 31B IT google/gemma/4-31b-it | Gemma | 27 | 262K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0/M output $0/M | 2026-04-02 | 2026-04-30 | ||
| Gemma 4 E2B IT google/gemma/4-e2b-it | Gemma | 1 | 131K | 8.2K | TextImageAudio | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-04-02 | 2026-04-02 | ||
| Gemma 4 E4B IT google/gemma/4-e4b-it | Gemma | 1 | 131K | 8.2K | TextImageAudio | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-04-02 | 2026-04-02 | ||
| Step 3.5 Flash 2603 stepfun/step/3-5-flash-2603 | StepFun | Step | 5 | 256K | 256K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.1/M · cache read $0.02/M output $0.3/M | 2026-04-02 | 2026-04-02 | |
| GLM-5V-Turbo zhipuai/glm/5v-turbo | Zhipu AI | GLM | 11 | 200K | 131K | TextImageVideoDocument | Text | Yes | Yes | -No | Yes | Closed | input $5/M · cache read $1.2/M output $22/M · cache write $0/M | 2026-04-01 | 2026-05-09 | |
| Trinity Large Thinking arcee-ai/trinity/large-thinking | Arcee Ai | Trinity | 4 | 262K | 262K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-04-01 | 2026-04-03 | |
| Veo 3.1 Lite Preview google/veo/3-1-lite-generate-preview | Veo | 1 | 1K | - | TextImage | Video | -No | -No | -No | -No | Closed | output $0.05/video second | 2026-03-31 | 2026-03-31 | ||
| Llama Nemotron Rerank VL 1B v2 nvidia/nemotron/llama-nemotron-rerank-vl-1b-v2 | NVIDIA | Nemotron | 1 | 128K | 4.1K | TextImage | Text | -No | -No | -No | -No | Open weight | input $0/M output $0/M | 2026-03-31 | 2026-03-31 | |
| Grok 4.20 Multi-Agent xai/grok/4-20-multi-agent | xAI | Grok | 3 | 2M | - | TextImageDocument | Text | Yes | -No | Yes | Yes | Closed | Pricing unavailable | 2026-03-31 | 2026-03-31 | |
| Grok 4.20 xai/grok/4-20 | xAI | Grok | 3 | 2M | - | TextImageDocument | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-03-31 | 2026-03-31 | |
| KAT-Coder-Pro V2 kwaipilot/kat/coder-pro-v2 | Kwaipilot | Kat | 4 | 262K | 80K | Text | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-03-27 | 2026-03-30 | |
| Gemini 3.1 Flash Live Preview google/gemini/3-1-flash-live-preview | Gemini | 1 | 131K | 66K | TextImageVideoAudio | TextAudio | Yes | Yes | -No | Yes | Closed | input $0.75/M output $4.5/M | 2026-03-26 | 2026-03-26 | ||
| Lyria 3 Clip Preview google/lyria/3-clip-preview | Lyria | 3 | 131K | 66K | TextImage | TextAudio | -No | -No | -No | Yes | Closed | input $0/M output $0/M | 2026-03-25 | 2026-03-25 | ||
| Lyria 3 Pro Preview google/lyria/3-pro-preview | Lyria | 3 | 131K | 8.2K | TextImage | TextAudio | -No | -No | -No | Yes | Closed | input $0/M output $0/M | 2026-03-25 | 2026-03-25 | ||
| Nemotron Cascade 2 30B A3B nvidia/nemotron/cascade-2-30b-a3b | NVIDIA | Nemotron | 1 | 256K | 33K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-03-24 | 2026-04-09 | |
| Reka Edge rekaai/reka/edge | RERekaai | Reka | 2 | 16K | 16K | ImageTextVideo | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-03-20 | 2026-03-20 | |
| MiniMax-M2.7 minimax/minimax/m2-7 | MiniMax | Minimax | 27 | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.06/M output $1.2/M · cache write $0.375/M | 2026-03-18 | 2026-07-22 | |
| MiniMax-M2.7-highspeed minimax/minimax/m2-7-highspeed | MiniMax | Minimax | 14 | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M · cache read $0.06/M output $2.4/M · cache write $0.375/M | 2026-03-18 | 2026-05-27 | |
| MiMo-V2-Omni xiaomi/mimo/v2-omni | Xiaomi | MiMo | 5 | 262K | 131K | TextImageAudioVideoDocument | Text | Yes | Yes | -No | Yes | Open weight | input $0.14/M · cache read $0.0028/M output $0.28/M | 2026-03-18 | 2026-06-24 | |
| MiMo-V2-Pro xiaomi/mimo/v2-pro | Xiaomi | MiMo | 9 | 1M | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.435/M · cache read $0.0036/M output $0.87/M | 2026-03-18 | 2026-06-24 | |
| GPT-5.4 mini openai/gpt/5-4-mini | OpenAI | GPT | 28 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $0.75/M · cache read $0.075/M output $4.5/M | 2026-03-17 | 2026-03-20 | |
| GPT-5.4 nano openai/gpt/5-4-nano | OpenAI | GPT | 24 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $0.2/M · cache read $0.02/M output $1.25/M | 2026-03-17 | 2026-03-20 | |
| Mistral Small 4 mistral/mistral/small-2603 | Mistral AI | Mistral | 4 | 256K | 256K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0.15/M output $0.6/M | 2026-03-16 | 2026-06-11 | |
| Mistral Small (latest) mistral/mistral/small-latest | Mistral AI | Mistral | 2 | 256K | 256K | TextImage | Text | Yes | Yes | -No | Yes | Open weight | input $0.15/M output $0.6/M | 2026-03-16 | 2026-03-16 | |
| Nemotron VoiceChat nvidia/nemotron/voicechat | NVIDIA | Nemotron | 1 | 128K | 8.2K | TextAudio | Text | -No | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2026-03-16 | 2026-03-16 | |
| GLM-5-Turbo zhipuai/glm/5-turbo | Zhipu AI | GLM | 11 | 200K | 131K | Text | Text | Yes | Yes | Yes | Yes | Closed | input $1.2/M · cache read $0.24/M output $4/M · cache write $0/M | 2026-03-16 | 2026-03-20 | |
| Nemotron 3 Super 120B A12B nvidia/nemotron/3-super-120b-a12b | NVIDIA | Nemotron | 10 | 262K | 262K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.2/M output $0.8/M | 2026-03-11 | 2026-03-12 | |
| Seed-2.0-Lite bytedance-seed/seed/2-0-lite | Bytedance Seed | Seed | 3 | 262K | 131K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-03-10 | 2026-03-10 | |
| Grok 4.20 (Non-Reasoning) xai/grok/4-20-0309-non-reasoning | xAI | Grok | 2 | 1M | 30K | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | input $1.25/M · cache read $0.2/M output $2.5/M | 2026-03-09 | 2026-03-09 | |
| Grok 4.20 (Reasoning) xai/grok/4-20-0309-reasoning | xAI | Grok | 2 | 1M | 30K | TextImageDocument | Text | Yes | Yes | Yes | Yes | Closed | input $1.25/M · cache read $0.2/M output $2.5/M | 2026-03-09 | 2026-03-09 | |
| GPT-5.4 openai/gpt/5-4 | OpenAI | GPT | 34 | 1.1M | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $2.5/M · cache read $0.25/M output $15/M | 2026-03-05 | 2026-03-20 | |
| GPT-5.4 Pro openai/gpt/5-4-pro | OpenAI | GPT | 14 | 1.1M | 128K | TextImage | Text | Yes | Yes | -No | -No | Closed | input $30/M output $180/M | 2026-03-05 | 2026-03-20 | |
| Mercury 2 inception/mercury/2 | Inception | Mercury | 4 | 128K | 50K | Text | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-03-04 | 2026-03-06 | |
| Gemini 3.1 Flash Lite Preview google/gemini/3-1-flash-lite-preview | Gemini | 9 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $0.25/M · cache read $0.025/M output $1.5/M | 2026-03-03 | 2026-03-03 | ||
| GPT-5.3 Chat openai/gpt/5-3-chat | OpenAI | GPT | 9 | 128K | 16K | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | input $1.75/M · cache read $0.175/M output $14/M | 2026-03-03 | 2026-03-20 | |
| Nano Banana 2 google/gemini/3-1-flash-image-preview | Gemini | 7 | 66K | 66K | TextImageDocument | TextImage | Yes | -No | -No | Yes | Closed | input $0.5/M output $60/M | 2026-02-26 | 2026-02-27 | ||
| Seed-2.0-Mini bytedance-seed/seed/2-0-mini | Bytedance Seed | Seed | 2 | 262K | 131K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-02-26 | 2026-02-26 | |
| Qwen3.5-Flash alibaba/qwen/qwen3-5-flash-02-23 | Alibaba | Qwen | 2 | 1M | 66K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-02-25 | 2026-02-25 | |
| Qwen3.5 122B-A10B alibaba/qwen/qwen3-5-122b-a10b | Alibaba | Qwen | 12 | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.4/M output $3.2/M | 2026-02-23 | 2026-03-18 | |
| Qwen3.5 27B alibaba/qwen/qwen3-5-27b | Alibaba | Qwen | 9 | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.3/M output $2.4/M | 2026-02-23 | 2026-03-18 | |
| Qwen3.5 35B-A3B alibaba/qwen/qwen3-5-35b-a3b | Alibaba | Qwen | 10 | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.25/M output $2/M | 2026-02-23 | 2026-06-11 | |
| Qwen3.5 9B alibaba/qwen/qwen3-5-9b | Alibaba | Qwen | 14 | 262K | 66K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-02-23 | 2026-06-11 | |
| Aion-2.0 aion-labs/aion/2-0 | Aion Labs | Aion | 3 | 131K | 33K | Text | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2026-02-23 | 2026-02-23 | |
| Gemini 3.1 Pro Preview google/gemini/3-1-pro-preview | Gemini | 21 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $2/M · cache read $0.2/M output $12/M | 2026-02-19 | 2026-06-11 | ||
| Gemini 3.1 Pro Preview Custom Tools google/gemini/3-1-pro-preview-customtools | Gemini | 8 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $2/M · cache read $0.2/M output $12/M | 2026-02-19 | 2026-02-19 | ||
| Sarvam 30B sarvam/sarvam/30b | SASarvam AI | Sarvam | 3 | 128K | 128K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2026-02-18 | 2026-03-06 | |
| Claude Sonnet 4.6 anthropic/claude/sonnet-4-6 | Anthropic | Claude | 35 | 1M | 64K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $3/M · cache read $0.3/M output $15/M · cache write $3.75/M | 2026-02-17 | 2026-06-11 | |
| Qwen3.5 Plus alibaba/qwen/qwen3-5-plus | Alibaba | Qwen | 8 | 1M | 66K | TextImageVideo | Text | Yes | Yes | -No | Yes | Closed | input $0.4/M output $2.4/M | 2026-02-16 | 2026-02-16 | |
| Qwen3.5 Plus 2026-02-15 alibaba/qwen/qwen3-5-plus-02-15 | Alibaba | Qwen | 2 | 1M | 66K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-02-16 | 2026-02-16 | |
| Qwen3.5 397B-A17B alibaba/qwen/qwen3-5-397b-a17b | Alibaba | Qwen | 20 | 262K | 66K | TextImageVideoAudio | Text | Yes | Yes | Yes | Yes | Open weight | input $0.6/M output $3.6/M | 2026-02-15 | 2026-06-11 | |
| MiniMax-M2.5-highspeed minimax/minimax/m2-5-highspeed | MiniMax | Minimax | 10 | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M · cache read $0.06/M output $2.4/M · cache write $0.375/M | 2026-02-13 | 2026-02-14 | |
| MiniMax-M2.5 minimax/minimax/m2-5 | MiniMax | Minimax | 32 | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.03/M output $1.2/M · cache write $0.375/M | 2026-02-12 | 2026-04-16 | |
| GLM-5 zhipuai/glm/5 | Zhipu AI | GLM | 25 | 205K | 131K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $1/M · cache read $0.2/M output $3.2/M · cache write $0/M | 2026-02-12 | 2026-07-22 | |
| Llama Nemotron Embed VL 1B v2 nvidia/nemotron/llama-nemotron-embed-vl-1b-v2 | NVIDIA | Nemotron | 1 | 33K | 2K | TextImage | Text | -No | -No | -No | -No | Open weight | input $0/M output $0/M | 2026-02-10 | 2026-02-10 | |
| Qwen3 Max Thinking alibaba/qwen/qwen3-max-thinking | Alibaba | Qwen | 2 | 262K | 66K | Text | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-02-09 | 2026-02-09 | |
| Claude Opus 4.6 anthropic/claude/opus-4-6 | Anthropic | Claude | 30 | 1M | 128K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $5/M · cache read $0.5/M output $25/M · cache write $6.25/M | 2026-02-05 | 2026-07-17 | |
| GPT-5.3 Codex openai/gpt/5-3-codex | OpenAI | GPT | 23 | 400K | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $1.75/M · cache read $0.175/M output $14/M | 2026-02-05 | 2026-03-20 | |
| Qwen3 Coder Next alibaba/qwen/qwen3-coder-next | Alibaba | Qwen | 5 | 262K | 262K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2026-02-04 | 2026-02-04 | |
| Step 3.5 Flash stepfun/step/3-5-flash | StepFun | Step | 10 | 256K | 256K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.1/M · cache read $0.02/M output $0.3/M | 2026-01-29 | 2026-06-15 | |
| Solar Pro 3 upstage/solar/pro-3 | Upstage | Solar | 3 | 128K | - | Text | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-01-27 | 2026-03-03 | |
| MiniMax M2-her minimax/minimax/m2-her | MiniMax | Minimax | 3 | 66K | 2K | Text | Text | -No | -No | -No | Yes | Closed | Pricing unavailable | 2026-01-23 | 2026-01-24 | |
| Nemotron Content Safety Reasoning 4B nvidia/nemotron/content-safety-reasoning-4b | NVIDIA | Nemotron | 1 | 128K | 4.1K | Text | Text | Yes | -No | -No | -No | Open weight | input $0/M output $0/M | 2026-01-22 | 2026-01-22 | |
| Palmyra X5 writer/palmyra/x5 | WRWriter | Palmyra | 3 | 1M | 8.2K | Text | Text | -No | -No | -No | Yes | Closed | Pricing unavailable | 2026-01-21 | 2026-01-21 | |
| GLM-4.7-Flash zhipuai/glm/4-7-flash | Zhipu AI | GLM | 9 | 200K | 131K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0/M · cache read $0/M output $0/M · cache write $0/M | 2026-01-19 | 2026-01-19 | |
| GLM-4.7-FlashX zhipuai/glm/4-7-flashx | Zhipu AI | GLM | 4 | 200K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.07/M · cache read $0.01/M output $0.4/M · cache write $0/M | 2026-01-19 | 2026-01-20 | |
| GPT Audio openai/gpt/audio | OpenAI | GPT | 2 | 128K | 16K | TextAudio | TextAudio | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-01-19 | 2026-01-19 | |
| GPT Audio Mini openai/gpt/audio-mini | OpenAI | GPT | 2 | 128K | 16K | TextAudio | TextAudio | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-01-19 | 2026-01-19 | |
| Kimi K2.5 moonshotai/kimi/k2-5 | Moonshot AI | Kimi | 45 | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $0.6/M · cache read $0.1/M output $3/M | 2026-01 | 2026-07-22 | |
| MiniMax-M2.1 minimax/minimax/m2-1 | MiniMax | Minimax | 18 | 205K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M · cache read $0.03/M output $1.2/M · cache write $0.375/M | 2025-12-23 | 2026-01-01 | |
| Seed 1.6 Flash bytedance-seed/seed/1-6-flash | Bytedance Seed | Seed | 2 | 262K | 33K | ImageTextVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-12-23 | 2025-12-23 | |
| Seed 1.6 bytedance-seed/seed/1-6 | Bytedance Seed | Seed | 2 | 262K | 33K | ImageTextVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-12-23 | 2025-12-23 | |
| GLM-4.7 zhipuai/glm/4-7 | Zhipu AI | GLM | 21 | 205K | 131K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.6/M · cache read $0.11/M output $2.2/M · cache write $0/M | 2025-12-22 | 2025-12-23 | |
| Gemini 3 Flash Preview google/gemini/3-flash-preview | Gemini | 20 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $0.5/M · cache read $0.05/M output $3/M | 2025-12-17 | 2026-06-11 | ||
| MiMo-V2-Flash xiaomi/mimo/v2-flash | Xiaomi | MiMo | 5 | 262K | 66K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.14/M · cache read $0.0028/M output $0.28/M | 2025-12-16 | 2026-06-24 | |
| Nemotron 3 Nano 30B A3B nvidia/nemotron/3-nano-30b-a3b | NVIDIA | Nemotron | 7 | 262K | 262K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2025-12-15 | 2025-12-15 | |
| GPT-5.2 openai/gpt/5-2 | OpenAI | GPT | 28 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.75/M · cache read $0.175/M output $14/M | 2025-12-11 | 2026-01-01 | |
| GPT-5.2 Chat openai/gpt/5-2-chat-latest | OpenAI | GPT | 6 | 128K | 16K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.75/M · cache read $0.175/M output $14/M | 2025-12-11 | 2026-01-01 | |
| GPT-5.2 Codex openai/gpt/5-2-codex | OpenAI | GPT | 20 | 400K | 128K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $1.75/M · cache read $0.175/M output $14/M | 2025-12-11 | 2026-01-15 | |
| GPT-5.2 Pro openai/gpt/5-2-pro | OpenAI | GPT | 11 | 400K | 128K | TextImage | Text | Yes | Yes | -No | -No | Closed | input $21/M output $168/M | 2025-12-11 | 2026-01-01 | |
| GPT-5.2 Chat openai/gpt/5-2-chat | OpenAI | GPT | 3 | 128K | 16K | DocumentImageText | Text | -No | Yes | Yes | -No | Closed | Pricing unavailable | 2025-12-10 | 2025-12-11 | |
| Devstral 2 mistral/devstral/2512 | Mistral AI | Devstral | 4 | 262K | 262K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.4/M output $2/M | 2025-12-09 | 2025-12-09 | |
| GLM-4.6V zhipuai/glm/4-6v | Zhipu AI | GLM | 8 | 128K | 33K | TextImageVideo | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M output $0.9/M | 2025-12-08 | 2025-12-08 | |
| Relace Search relace/relace/search | Relace | Relace | 2 | 256K | 128K | Text | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2025-12-08 | 2025-12-08 | |
| Nova 2 Lite amazon/nova/2-lite-v1 | AMAmazon | Nova | 3 | 1M | 66K | TextImageVideoDocument | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2025-12-02 | 2025-12-02 | |
| Ministral 3 14B 2512 mistral/ministral/14b-2512 | Mistral AI | Ministral | 3 | 262K | - | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-12-02 | 2025-12-04 | |
| Ministral 3 8B 2512 mistral/ministral/8b-2512 | Mistral AI | Ministral | 3 | 262K | - | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-12-02 | 2025-12-04 | |
| Ministral 3 3B 2512 mistral/ministral/3b-2512 | Mistral AI | Ministral | 3 | 131K | - | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-12-02 | 2025-12-04 | |
| DeepSeek Chat deepseek/deepseek/chat | DeepSeek | DeepSeek | 8 | 1M | 384K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.14/M · cache read $0.0028/M output $0.28/M | 2025-12-01 | 2026-02-28 | |
| DeepSeek Reasoner deepseek/deepseek/reasoner | DeepSeek | DeepSeek | 5 | 1M | 384K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.14/M · cache read $0.0028/M output $0.28/M | 2025-12-01 | 2026-02-28 | |
| DeepSeek V3.2 deepseek/deepseek/v3-2 | DeepSeek | DeepSeek | 7 | 164K | 66K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-12-01 | 2025-12-05 | |
| GPT-Image-1.5 openai/gpt/image-1-5 | OpenAI | GPT | 4 | - | - | TextImage | TextImage | -No | -No | -No | -No | Closed | input $8/M · cache read $2/M output $32/M | 2025-11-25 | 2025-12-16 | |
| Olmo 3 32B Think allenai/olmo/3-32b-think | Allenai | Olmo | 2 | 66K | 66K | Text | Text | Yes | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-11-21 | 2025-11-21 | |
| Nano Banana Pro google/gemini/3-pro-image-preview | Gemini | 7 | 66K | 33K | TextImage | TextImage | Yes | -No | -No | Yes | Closed | input $2/M output $120/M | 2025-11-20 | 2025-11-20 | ||
| Gemini 3 Pro Preview google/gemini/3-pro-preview | Gemini | 9 | 1M | 66K | TextImageVideoAudioDocument | Text | Yes | Yes | Yes | Yes | Closed | input $2/M · cache read $0.2/M output $12/M | 2025-11-18 | 2026-01-01 | ||
| GPT-5.1 openai/gpt/5-1 | OpenAI | GPT | 24 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.25/M · cache read $0.125/M output $10/M | 2025-11-13 | 2026-02-01 | |
| GPT-5.1 Chat openai/gpt/5-1-chat-latest | OpenAI | GPT | 5 | 128K | 16K | TextImage | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2025-11-13 | 2025-11-14 | |
| GPT-5.1 Codex openai/gpt/5-1-codex | OpenAI | GPT | 18 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.25/M · cache read $0.125/M output $10/M | 2025-11-13 | 2026-01-01 | |
| GPT-5.1 Codex Max openai/gpt/5-1-codex-max | OpenAI | GPT | 13 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.25/M · cache read $0.125/M output $10/M | 2025-11-13 | 2026-01-01 | |
| GPT-5.1 Codex mini openai/gpt/5-1-codex-mini | OpenAI | GPT | 16 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $0.25/M · cache read $0.025/M output $2/M | 2025-11-13 | 2026-01-01 | |
| Cogito v2.1 671B deepcogito/cogito/v2-1-671b | DEDeepcogito | Cogito | 2 | 128K | - | Text | Text | Yes | -No | Yes | Yes | Closed | Pricing unavailable | 2025-11-13 | 2025-11-13 | |
| Kimi K2 Thinking moonshotai/kimi/k2-thinking | Moonshot AI | Kimi | 19 | 262K | 262K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M · cache read $0.15/M output $2.5/M | 2025-11-06 | 2026-06-29 | |
| Kimi K2 Thinking Turbo moonshotai/kimi/k2-thinking-turbo | Moonshot AI | Kimi | 4 | 262K | 262K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $1.15/M · cache read $0.15/M output $8/M | 2025-11-06 | 2025-11-06 | |
| Claude Opus 4.5 anthropic/claude/opus-4-5-20251101 | Anthropic | Claude | 24 | 200K | 64K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $5/M · cache read $0.5/M output $25/M · cache write $6.25/M | 2025-11-01 | 2026-06-11 | |
| Nova Premier 1.0 amazon/nova/premier-v1 | AMAmazon | Nova | 2 | 1M | 32K | TextImage | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2025-10-31 | 2025-10-31 | |
| Sonar Pro Search perplexity/sonar/pro-search | Perplexity | Sonar | 2 | 200K | 8K | TextImage | Text | Yes | -No | Yes | Yes | Closed | Pricing unavailable | 2025-10-30 | 2025-10-30 | |
| Voxtral Small 24B 2507 mistral/voxtral/small-24b-2507 | Mistral AI | Voxtral | 2 | 32K | - | TextAudioDocument | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-30 | 2025-10-30 | |
| GPT OSS Safeguard 120B openai/gpt/oss-safeguard-120b | OpenAI | GPT | 2 | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-29 | 2025-10-29 | |
| gpt-oss-safeguard-20b openai/gpt/oss-safeguard-20b | OpenAI | GPT | 5 | 131K | 66K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-29 | 2026-06-29 | |
| Llama 3.1 Nemotron Safety Guard 8B v3 nvidia/nemotron/llama-3-1-nemotron-safety-guard-8b-v3 | NVIDIA | Nemotron | 1 | 128K | 4.1K | Text | Text | -No | -No | -No | -No | Open weight | input $0/M output $0/M | 2025-10-28 | 2025-10-28 | |
| Nemotron Nano 12B v2 VL nvidia/nemotron/nano-12b-v2-vl | NVIDIA | Nemotron | 4 | 128K | 128K | TextImageVideo | Text | Yes | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2025-10-28 | 2025-10-28 | |
| MiniMax-M2 minimax/minimax/m2 | MiniMax | Minimax | 15 | 197K | 128K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.3/M output $1.2/M | 2025-10-27 | 2025-10-28 | |
| Qwen3 VL 32B Instruct alibaba/qwen/qwen3-vl-32b-instruct | Alibaba | Qwen | 2 | 131K | 33K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-23 | 2025-10-23 | |
| Granite 4.0 Micro ibm-granite/granite/4-0-h-micro | Ibm Granite | Granite | 2 | 131K | 131K | Text | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2025-10-20 | 2025-10-20 | |
| GPT-5 Image Mini openai/gpt/5-image-mini | OpenAI | GPT | 2 | 400K | 128K | DocumentImageText | ImageText | Yes | -No | Yes | Yes | Closed | Pricing unavailable | 2025-10-16 | 2025-10-16 | |
| Claude Haiku 4.5 anthropic/claude/haiku-4-5-20251001 | Anthropic | Claude | 35 | 200K | 64K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $1/M · cache read $0.1/M output $5/M · cache write $1.25/M | 2025-10-15 | 2026-01-01 | |
| Veo 3.1 Fast Preview google/veo/3-1-fast-generate-preview | Veo | 1 | 1K | - | TextImageVideo | Video | -No | -No | -No | -No | Closed | output $0.1/video second | 2025-10-15 | 2026-01-01 | ||
| Veo 3.1 Preview google/veo/3-1-generate-preview | Veo | 1 | 1K | 1 | TextImage | Video | -No | -No | -No | -No | Closed | output $0.4/video second | 2025-10-15 | 2026-01-01 | ||
| Qwen3 VL 8B Thinking alibaba/qwen/qwen3-vl-8b-thinking | Alibaba | Qwen | 2 | 131K | 33K | ImageText | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-14 | 2025-10-14 | |
| Qwen3 VL 8B Instruct alibaba/qwen/qwen3-vl-8b-instruct | Alibaba | Qwen | 3 | 262K | 33K | ImageText | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-14 | 2025-10-17 | |
| GPT-5 Image openai/gpt/5-image | OpenAI | GPT | 3 | 400K | 128K | ImageTextDocument | ImageText | Yes | -No | Yes | Yes | Closed | Pricing unavailable | 2025-10-14 | 2025-10-14 | |
| Gemini 2.5 Computer Use Preview google/gemini/2-5-computer-use-preview-10-2025 | Gemini | 1 | 128K | 64K | TextImage | Text | Yes | Yes | -No | Yes | Closed | input $1.25/M output $10/M | 2025-10-07 | 2025-10-07 | ||
| GPT-5 Pro openai/gpt/5-pro | OpenAI | GPT | 14 | 400K | 272K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $15/M output $120/M | 2025-10-06 | 2026-01-01 | |
| Qwen3 VL 30B A3B Thinking alibaba/qwen/qwen3-vl-30b-a3b-thinking | Alibaba | Qwen | 3 | 262K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-06 | 2025-10-11 | |
| Qwen3 VL 30B A3B Instruct alibaba/qwen/qwen3-vl-30b-a3b-instruct | Alibaba | Qwen | 3 | 262K | 33K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-10-06 | 2025-10-11 | |
| Gemini 2.5 Flash TTS google/gemini/2-5-flash-tts | Gemini | 1 | 33K | 16K | Text | Audio | -No | -No | -No | Yes | Closed | input $0.5/M output $10/M | 2025-09-30 | 2025-12-10 | ||
| Gemini 2.5 Pro TTS google/gemini/2-5-pro-tts | Gemini | 1 | 33K | 16K | Text | Audio | -No | -No | -No | -No | Closed | input $1/M output $20/M | 2025-09-30 | 2025-12-10 | ||
| GLM-4.6 zhipuai/glm/4-6 | Zhipu AI | GLM | 14 | 205K | 131K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.6/M · cache read $0.11/M output $2.2/M · cache write $0/M | 2025-09-30 | 2025-11-13 | |
| Claude Sonnet 4.5 anthropic/claude/sonnet-4-5-20250929 | Anthropic | Claude | 28 | 200K | 64K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $3/M · cache read $0.3/M output $15/M · cache write $3.75/M | 2025-09-29 | 2026-06-11 | |
| DeepSeek V3.2 Exp deepseek/deepseek/v3-2-exp | DeepSeek | DeepSeek | 5 | 164K | 66K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-09-29 | 2025-09-29 | |
| Cydonia 24B V4.1 thedrummer/cydonia/24b-v4-1 | THThedrummer | Cydonia | 2 | 131K | 131K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-09-27 | 2025-09-27 | |
| Relace Apply 3 relace/relace/apply-3 | Relace | Relace | 2 | 256K | 128K | Text | Text | -No | -No | -No | -No | Closed | Pricing unavailable | 2025-09-26 | 2025-09-26 | |
| Qwen3 Max alibaba/qwen/qwen3-max | Alibaba | Qwen | 15 | 262K | 66K | Text | Text | -No | Yes | Yes | Yes | Closed | input $1.2/M output $6/M | 2025-09-23 | 2026-01-23 | |
| Qwen3-VL Plus alibaba/qwen/qwen3-vl-plus | Alibaba | Qwen | 4 | 262K | 33K | TextImage | Text | Yes | Yes | -No | Yes | Closed | input $0.2/M output $1.6/M | 2025-09-23 | 2025-09-23 | |
| Qwen3 VL 235B A22B Thinking alibaba/qwen/qwen3-vl-235b-a22b-thinking | Alibaba | Qwen | 3 | 131K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-09-23 | 2025-09-24 | |
| Qwen3 VL 235B A22B Instruct alibaba/qwen/qwen3-vl-235b-a22b-instruct | Alibaba | Qwen | 4 | 262K | 33K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-09-23 | 2025-09-24 | |
| DeepSeek V3.1 Terminus deepseek/deepseek/v3-1-terminus | DeepSeek | DeepSeek | 5 | 164K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-09-22 | 2025-09-22 | |
| GPT-5-Codex openai/gpt/5-codex | OpenAI | GPT | 13 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.25/M · cache read $0.13/M output $10/M | 2025-09-15 | 2026-01-01 | |
| Qwen Plus 0728 alibaba/qwen/plus-2025-07-28 | Alibaba | Qwen | 2 | 1M | 33K | Text | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-09-08 | 2025-09-08 | |
| Qwen Plus 0728 (thinking) alibaba/qwen/plus-2025-07-28-thinking | Alibaba | Qwen | 2 | 1M | 33K | Text | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-09-08 | 2025-09-08 | |
| Kimi K2 0905 moonshotai/kimi/k2-0905 | Moonshot AI | Kimi | 6 | 262K | 100K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-09-04 | 2026-01-01 | |
| Sarvam 105B sarvam/sarvam/105b | SASarvam AI | Sarvam | 3 | 131K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input INR4/M · cache read INR2.5/M output INR16/M | 2025-09-01 | 2026-03-06 | |
| Qwen3-Next 80B-A3B Instruct alibaba/qwen/qwen3-next-80b-a3b-instruct | Alibaba | Qwen | 14 | 131K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.5/M output $2/M | 2025-09 | 2026-07-22 | |
| Qwen3-Next 80B-A3B (Thinking) alibaba/qwen/qwen3-next-80b-a3b-thinking | Alibaba | Qwen | 12 | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.5/M output $6/M | 2025-09 | 2026-01-01 | |
| Command A Translate cohere/command/a-translate-08-2025 | Cohere | Command | 1 | 8K | 8K | Text | Text | -No | Yes | -No | Yes | Open weight | input $2.5/M output $10/M | 2025-08-28 | 2025-08-28 | |
| Qwen3 30B A3B Thinking 2507 alibaba/qwen/qwen3-30b-a3b-thinking-2507 | Alibaba | Qwen | 2 | 82K | 33K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-08-28 | 2025-08-28 | |
| Nano Banana google/gemini/2-5-flash-image | Gemini | 8 | 33K | 33K | TextImage | TextImage | Yes | -No | -No | Yes | Closed | input $0.3/M · cache read $0.075/M output $30/M | 2025-08-26 | 2025-10-22 | ||
| Hermes 4 70B nousresearch/hermes/4-70b | NONousresearch | Hermes | 2 | 131K | - | Text | Text | Yes | -No | -No | Yes | Open weight | Pricing unavailable | 2025-08-26 | 2025-08-26 | |
| Hermes 4 405B nousresearch/hermes/4-405b | NONousresearch | Hermes | 2 | 131K | - | Text | Text | Yes | -No | -No | Yes | Open weight | Pricing unavailable | 2025-08-26 | 2025-08-26 | |
| Command A Reasoning cohere/command/a-reasoning-08-2025 | Cohere | Command | 2 | 256K | 32K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $2.5/M output $10/M | 2025-08-21 | 2025-08-21 | |
| DeepSeek V3.1 deepseek/deepseek/chat-v3-1 | DeepSeek | DeepSeek | 3 | 164K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-08-21 | 2025-08-21 | |
| Nemotron Nano 9B v2 nvidia/nemotron/nano-9b-v2 | NVIDIA | Nemotron | 4 | 131K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-08-18 | 2025-08-18 | |
| Mistral Medium 3.1 mistral/mistral/medium-3-1 | Mistral AI | Mistral | 3 | 131K | - | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-08-13 | 2025-09-05 | |
| GLM-4.5V zhipuai/glm/4-5v | Zhipu AI | GLM | 7 | 64K | 16K | TextImageVideo | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M output $1.8/M | 2025-08-11 | 2025-08-12 | |
| Jamba Large 1.7 ai21/jamba/large-1-7 | AIAi21 | Jamba | 2 | 256K | 4.1K | Text | Text | -No | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-08-08 | 2025-08-08 | |
| GPT-5 openai/gpt/5 | OpenAI | GPT | 24 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.25/M · cache read $0.125/M output $10/M | 2025-08-07 | 2025-09-19 | |
| GPT-5 Chat (latest) openai/gpt/5-chat-latest | OpenAI | GPT | 5 | 400K | 128K | TextImage | Text | Yes | -No | Yes | Yes | Closed | Pricing unavailable | 2025-08-07 | 2026-01-01 | |
| GPT-5 Mini openai/gpt/5-mini | OpenAI | GPT | 26 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $0.25/M · cache read $0.025/M output $2/M | 2025-08-07 | 2026-01-01 | |
| GPT-5 Nano openai/gpt/5-nano | OpenAI | GPT | 21 | 400K | 128K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $0.05/M · cache read $0.005/M output $0.4/M | 2025-08-07 | 2026-01-01 | |
| Claude Opus 4.1 anthropic/claude/opus-4-1-20250805 | Anthropic | Claude | 22 | 200K | 32K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | input $15/M · cache read $1.5/M output $75/M · cache write $18.75/M | 2025-08-05 | 2026-01-01 | |
| GPT OSS 120B openai/gpt/oss-120b | OpenAI | GPT | 47 | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0/M output $0/M | 2025-08-05 | 2026-07-22 | |
| GPT OSS 20B openai/gpt/oss-20b | OpenAI | GPT | 29 | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0/M output $0/M | 2025-08-05 | 2026-03-01 | |
| Codestral 2508 mistral/codestral/2508 | Mistral AI | Codestral | 3 | 256K | - | TextDocument | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-08-01 | 2025-08-01 | |
| Command A Vision cohere/command/a-vision-07-2025 | Cohere | Command | 1 | 128K | 8K | TextImage | Text | -No | -No | -No | Yes | Open weight | input $2.5/M output $10/M | 2025-07-31 | 2025-07-31 | |
| Qwen3 30B A3B Instruct 2507 alibaba/qwen/qwen3-30b-a3b-instruct-2507 | Alibaba | Qwen | 2 | 262K | 32K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-07-29 | 2025-07-29 | |
| Qwen Flash alibaba/qwen/flash | Alibaba | Qwen | 4 | 1M | 33K | Text | Text | Yes | Yes | -No | Yes | Closed | input $0.05/M output $0.4/M | 2025-07-28 | 2025-07-28 | |
| Qwen3 Coder Flash alibaba/qwen/qwen3-coder-flash | Alibaba | Qwen | 8 | 1M | 66K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.3/M output $1.5/M | 2025-07-28 | 2026-04-30 | |
| GLM-4.5 zhipuai/glm/4-5 | Zhipu AI | GLM | 11 | 131K | 98K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.6/M · cache read $0.11/M output $2.2/M · cache write $0/M | 2025-07-28 | 2025-08-05 | |
| GLM-4.5-Air zhipuai/glm/4-5-air | Zhipu AI | GLM | 10 | 131K | 98K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.2/M · cache read $0.03/M output $1.1/M · cache write $0/M | 2025-07-28 | 2025-08-05 | |
| GLM-4.5-Flash zhipuai/glm/4-5-flash | Zhipu AI | GLM | 4 | 131K | 98K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0/M · cache read $0/M output $0/M · cache write $0/M | 2025-07-28 | 2025-07-28 | |
| Llama 3.3 Nemotron Super 49B v1.5 nvidia/nemotron/llama-3-3-nemotron-super-49b-v1-5 | NVIDIA | Nemotron | 3 | 131K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2025-07-25 | 2025-07-25 | |
| Qwen3 235B A22B Thinking 2507 alibaba/qwen/qwen3-235b-a22b-thinking-2507 | Alibaba | Qwen | 4 | 262K | - | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-07-25 | 2026-01-01 | |
| Qwen3 Coder Plus alibaba/qwen/qwen3-coder-plus | Alibaba | Qwen | 12 | 1M | 66K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $1/M output $5/M | 2025-07-23 | 2025-07-23 | |
| Qwen3 Coder 480B A35B alibaba/qwen/qwen3-coder | Alibaba | Qwen | 4 | 262K | 66K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-07-23 | 2026-03-17 | |
| UI-TARS 7B bytedance/ui/tars-1-5-7b | BYBytedance | Ui | 2 | 128K | 2K | ImageText | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-07-22 | 2025-07-22 | |
| Qwen3 235B A22B Instruct 2507 alibaba/qwen/qwen3-235b-a22b-2507 | Alibaba | Qwen | 3 | 262K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-07-21 | 2025-07-21 | |
| Kimi K2 0711 moonshotai/kimi/k2 | Moonshot AI | Kimi | 4 | 131K | 100K | Text | Text | -No | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-07-11 | 2025-09-05 | |
| Devstral Medium mistral/devstral/medium-2507 | Mistral AI | Devstral | 2 | 128K | 128K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.4/M output $2/M | 2025-07-10 | 2025-07-10 | |
| Devstral Small mistral/devstral/small-2507 | Mistral AI | Devstral | 2 | 128K | 128K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.1/M output $0.3/M | 2025-07-10 | 2025-07-10 | |
| Uncensored cognitivecomputations/dolphin/mistral-24b-venice-edition | COCognitivecomputations | Dolphin | 2 | 128K | 8.2K | Text | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2025-07-09 | 2025-07-09 | |
| Hunyuan A13B Instruct tencent/hunyuan/a13b-instruct | Tencent | Hunyuan | 2 | 131K | 131K | Text | Text | Yes | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-07-08 | 2025-07-08 | |
| Morph V3 Large morph/morph/v3-large | MOMorph | Morph | 4 | 262K | 131K | Text | Text | -No | -No | Yes | Yes | Closed | Pricing unavailable | 2025-07-07 | 2025-07-07 | |
| Morph V3 Fast morph/morph/v3-fast | MOMorph | Morph | 4 | 82K | 38K | Text | Text | -No | -No | -No | Yes | Closed | Pricing unavailable | 2025-07-07 | 2025-07-07 | |
| ERNIE 4.5 VL 424B A47B baidu/ernie/4-5-vl-424b-a47b | BABaidu | Ernie | 4 | 123K | 16K | ImageText | Text | Yes | -No | -No | Yes | Open weight | Pricing unavailable | 2025-06-30 | 2026-01-01 | |
| Mistral Small 3.2 mistral/mistral/small-2506 | Mistral AI | Mistral | 2 | 128K | 16K | TextImage | Text | -No | Yes | -No | Yes | Open weight | input $0.1/M output $0.3/M | 2025-06-20 | 2025-06-20 | |
| Mistral Small 3.2 24B mistral/mistral/small-3-2-24b-instruct | Mistral AI | Mistral | 2 | 256K | 16K | ImageText | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-06-20 | 2025-06-20 | |
| Gemini 2.5 Flash google/gemini/2-5-flash | Gemini | 29 | 1M | 66K | TextImageAudioVideoDocument | Text | Yes | Yes | Yes | Yes | Closed | input $0.3/M · cache read $0.03/M output $2.5/M | 2025-06-17 | 2026-01-01 | ||
| Gemini 2.5 Flash-Lite google/gemini/2-5-flash-lite | Gemini | 18 | 1M | 66K | TextImageAudioVideoDocument | Text | Yes | Yes | Yes | Yes | Closed | input $0.1/M · cache read $0.01/M output $0.4/M | 2025-06-17 | 2026-01-01 | ||
| Gemini 2.5 Pro google/gemini/2-5-pro | Gemini | 29 | 1M | 66K | TextImageAudioVideoDocument | Text | Yes | Yes | Yes | Yes | Closed | input $1.25/M · cache read $0.125/M output $10/M | 2025-06-17 | 2026-01-01 | ||
| MiniMax M1 minimax/minimax/m1 | MiniMax | Minimax | 2 | 1M | 40K | Text | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2025-06-17 | 2025-06-17 | |
| Mistral Nemotron nvidia/nemotron/mistral-nemotron | NVIDIA | Nemotron | - | 128K | 8.2K | Text | Text | -No | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-06-11 | 2025-06-12 | |
| o3-pro openai/o-series/o3-pro | OpenAI | o-series | 8 | 200K | 100K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $20/M output $80/M | 2025-06-10 | 2025-06-10 | |
| Gemini 2.5 Pro Preview 06-05 google/gemini/2-5-pro-preview | Gemini | 2 | 1M | 66K | DocumentImageTextAudio | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-06-05 | 2025-06-05 | ||
| R1 0528 deepseek/deepseek/r1-0528 | DeepSeek | DeepSeek | 5 | 164K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-05-28 | 2026-01-01 | |
| Claude Opus 4 anthropic/claude/opus-4-20250514 | Anthropic | Claude | 5 | 200K | 32K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2025-05-22 | 2026-01-01 | |
| Claude Sonnet 4 anthropic/claude/sonnet-4-20250514 | Anthropic | Claude | 5 | 200K | 64K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2025-05-22 | 2026-01-01 | |
| Claude Opus 4 anthropic/claude/opus-4 | Anthropic | Claude | 8 | 200K | 32K | ImageTextDocument | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2025-05-22 | 2025-05-22 | |
| Claude Sonnet 4 anthropic/claude/sonnet-4 | Anthropic | Claude | 9 | 1M | 64K | ImageTextDocument | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2025-05-22 | 2025-05-22 | |
| Gemini Embedding 001 google/gemini/embedding-001 | Gemini | 4 | 2K | 1 | Text | Text | -No | -No | -No | -No | Closed | input $0.15/M output $0/M | 2025-05-20 | 2025-05-20 | ||
| Gemma 3n 4B google/gemma/3n-e4b-it | Gemma | 3 | 33K | - | Text | Text | -No | -No | Yes | Yes | Open weight | input $0/M output $0/M | 2025-05-20 | 2025-06-03 | ||
| Mistral Medium 3 mistral/mistral/medium-2505 | Mistral AI | Mistral | 4 | 131K | 131K | TextImage | Text | -No | Yes | -No | Yes | Closed | input $0.4/M output $2/M | 2025-05-07 | 2025-05-07 | |
| Mistral Medium 3 mistral/mistral/medium-3 | Mistral AI | Mistral | 3 | 131K | - | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-05-07 | 2025-09-25 | |
| Gemini 2.5 Pro Preview 05-06 google/gemini/2-5-pro-preview-05-06 | Gemini | 2 | 1M | 66K | TextImageDocumentAudioVideo | Text | Yes | Yes | Yes | Yes | Closed | Pricing unavailable | 2025-05-07 | 2025-05-07 | ||
| Virtuoso Large arcee-ai/virtuoso/large | Arcee Ai | Virtuoso | 2 | 131K | 64K | Text | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2025-05-05 | 2025-05-05 | |
| Llama Guard 4 12B meta/llama/guard-4-12b | Meta | Llama | 2 | 1M | 16K | ImageText | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2025-04-30 | 2025-04-30 | |
| Qwen3 30B A3B alibaba/qwen/qwen3-30b-a3b | Alibaba | Qwen | 3 | 131K | 16K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-04-28 | 2025-04-28 | |
| Qwen3 8B alibaba/qwen/qwen3-8b | Alibaba | Qwen | 2 | 131K | 8.2K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-04-28 | 2025-04-28 | |
| Qwen3 14B alibaba/qwen/qwen3-14b | Alibaba | Qwen | 3 | 131K | 8.2K | Text | Text | Yes | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-04-28 | 2025-04-28 | |
| GPT-Image-1 openai/gpt/image-1 | OpenAI | GPT | 4 | - | - | TextImage | Image | -No | -No | -No | -No | Closed | input $10/M · cache read $2.5/M output $40/M | 2025-04-24 | 2025-04-24 | |
| o3 openai/o-series/o3 | OpenAI | o-series | 17 | 200K | 100K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $2/M · cache read $0.5/M output $8/M | 2025-04-16 | 2026-01-01 | |
| o4-mini openai/o-series/o4-mini | OpenAI | o-series | 19 | 200K | 100K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $1.1/M · cache read $0.275/M output $4.4/M | 2025-04-16 | 2026-01-01 | |
| o4 Mini High openai/o-series/o4-mini-high | OpenAI | o-series | 3 | 200K | 100K | ImageTextDocument | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2025-04-16 | 2025-04-16 | |
| Llama 3.1 Nemotron 70B Instruct nvidia/nemotron/llama-3-1-nemotron-70b-instruct | NVIDIA | Nemotron | 1 | 128K | 8.2K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2025-04-15 | 2025-04-15 | |
| GPT-4.1 openai/gpt/4-1 | OpenAI | GPT | 24 | 1M | 33K | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | input $2/M · cache read $0.5/M output $8/M | 2025-04-14 | 2025-04-14 | |
| GPT-4.1 mini openai/gpt/4-1-mini | OpenAI | GPT | 21 | 1M | 33K | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | input $0.4/M · cache read $0.1/M output $1.6/M | 2025-04-14 | 2025-04-15 | |
| GPT-4.1 nano openai/gpt/4-1-nano | OpenAI | GPT | 18 | 1M | 33K | TextImage | Text | -No | Yes | Yes | Yes | Closed | input $0.1/M · cache read $0.025/M output $0.4/M | 2025-04-14 | 2025-04-15 | |
| Llama 3.1 Nemotron Ultra 253B nvidia/nemotron/llama-3-1-nemotron-ultra-253b | NVIDIA | Nemotron | 1 | 128K | 8.2K | Text | Text | Yes | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-04-07 | 2025-04-07 | |
| Llama 3.3 Nemotron Super 49B v1 nvidia/nemotron/llama-3-3-nemotron-super-49b-v1 | NVIDIA | Nemotron | 2 | 131K | 131K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2025-04-07 | 2025-08-08 | |
| Llama 4 Maverick 17B Instruct meta/llama/4-maverick-17b-instruct | Meta | Llama | 1 | 1M | 16K | TextImage | Text | -No | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-04-05 | 2025-04-05 | |
| Llama 4 Scout 17B Instruct meta/llama/4-scout-17b-instruct | Meta | Llama | 1 | 3.5M | 16K | TextImage | Text | -No | Yes | -No | Yes | Open weight | Pricing unavailable | 2025-04-05 | 2025-04-05 | |
| Llama 4 Maverick meta/llama/4-maverick | Meta | Llama | 3 | 1M | 16K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-04-05 | 2025-09-05 | |
| Llama 4 Scout meta/llama/4-scout | Meta | Llama | 3 | 1.3M | 16K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-04-05 | 2025-09-05 | |
| Qwen3 235B-A22B alibaba/qwen/qwen3-235b-a22b | Alibaba | Qwen | 8 | 131K | 16K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.7/M output $2.8/M | 2025-04 | 2025-08-05 | |
| Qwen3 32B alibaba/qwen/qwen3-32b | Alibaba | Qwen | 13 | 131K | 16K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.7/M output $2.8/M | 2025-04 | 2025-08-05 | |
| Qwen3-Coder 30B-A3B Instruct alibaba/qwen/qwen3-coder-30b-a3b-instruct | Alibaba | Qwen | 13 | 262K | 66K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.45/M output $2.25/M | 2025-04 | 2026-03-17 | |
| Qwen3-Coder 480B-A35B Instruct alibaba/qwen/qwen3-coder-480b-a35b-instruct | Alibaba | Qwen | 6 | 262K | 66K | Text | Text | -No | Yes | -No | Yes | Open weight | input $1.5/M output $7.5/M | 2025-04 | 2025-08-14 | |
| DeepSeek V3 0324 deepseek/deepseek/chat-v3-0324 | DeepSeek | DeepSeek | 2 | 164K | 66K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-03-24 | 2025-03-24 | |
| o1-pro openai/o-series/o1-pro | OpenAI | o-series | 5 | 200K | 100K | TextImage | Text | Yes | Yes | Yes | -No | Closed | input $150/M output $600/M | 2025-03-19 | 2025-03-19 | |
| Magistral Medium (latest) mistral/magistral/medium-latest | Mistral AI | Magistral | 2 | 128K | 16K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $2/M output $5/M | 2025-03-17 | 2025-03-20 | |
| Mistral Small 3.1 24B mistral/mistral/small-3-1-24b-instruct | Mistral AI | Mistral | 2 | 128K | 128K | TextImage | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2025-03-17 | 2025-03-17 | |
| Command A cohere/command/a-03-2025 | Cohere | Command | 2 | 256K | 8K | Text | Text | -No | Yes | -No | Yes | Open weight | input $2.5/M output $10/M | 2025-03-13 | 2025-03-13 | |
| Gemma 3 4B google/gemma/3-4b-it | Gemma | 3 | 131K | 16K | TextImage | Text | -No | -No | Yes | Yes | Open weight | input $0/M output $0/M | 2025-03-13 | 2025-03-13 | ||
| Gemma 3 12B google/gemma/3-12b-it | Gemma | 4 | 131K | 16K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | input $0/M output $0/M | 2025-03-13 | 2025-03-13 | ||
| Command A cohere/command/a | Cohere | Command | 3 | 256K | 8.2K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-03-13 | 2025-03-13 | |
| Reka Flash 3 rekaai/reka/flash-3 | RERekaai | Reka | 2 | 66K | 66K | Text | Text | Yes | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-03-12 | 2025-03-12 | |
| Gemma 3 27B google/gemma/3-27b-it | Gemma | 5 | 262K | 131K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-03-12 | 2026-02-04 | ||
| Skyfall 36B V2 thedrummer/skyfall/36b-v2 | THThedrummer | Skyfall | 2 | 33K | 33K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-03-10 | 2025-03-10 | |
| Sonar Deep Research perplexity/sonar/deep-research | Perplexity | Sonar | 3 | 128K | - | Text | Text | Yes | -No | -No | Yes | Closed | input $2/M output $8/M | 2025-03-07 | 2025-09-01 | |
| QwQ Plus alibaba/qwen/qwq-plus | Alibaba | Qwen | 2 | 131K | 8.2K | Text | Text | Yes | Yes | -No | Yes | Closed | input $0.8/M output $2.4/M | 2025-03-05 | 2025-03-05 | |
| Aya Vision 32B cohere/aya/c4ai-aya-vision-32b | Cohere | Aya | 1 | 16K | 4K | TextImage | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2025-03-04 | 2025-05-14 | |
| Aya Vision 8B cohere/aya/c4ai-aya-vision-8b | Cohere | Aya | 1 | 16K | 4K | TextImage | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2025-03-04 | 2025-05-14 | |
| Command R7B Arabic cohere/command/r7b-arabic-02-2025 | Cohere | Command | 1 | 128K | 4K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.0375/M output $0.15/M | 2025-02-27 | 2025-02-27 | |
| Claude Sonnet 3.7 anthropic/claude/3-7-sonnet-20250219 | Anthropic | Claude | 2 | 200K | 64K | TextImageDocument | Text | Yes | Yes | -No | Yes | Closed | Pricing unavailable | 2025-02-19 | 2025-02-19 | |
| Saba mistral/mistral/saba | Mistral AI | Mistral | 3 | 33K | - | TextDocument | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2025-02-17 | 2025-02-17 | |
| o3 Mini High openai/o-series/o3-mini-high | OpenAI | o-series | 4 | 200K | 100K | TextDocument | Text | Yes | Yes | Yes | -No | Closed | Pricing unavailable | 2025-02-12 | 2025-02-12 | |
| Aion-RP 1.0 (8B) aion-labs/aion/rp-llama-3-1-8b | Aion Labs | Aion | 3 | 33K | 33K | Text | Text | -No | -No | -No | Yes | Closed | Pricing unavailable | 2025-02-04 | 2025-02-04 | |
| Mistral Small 3 mistral/mistral/small-24b-instruct-2501 | Mistral AI | Mistral | 2 | 33K | 16K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-01-30 | 2025-01-30 | |
| R1 Distill Llama 70B deepseek/deepseek/r1-distill-llama-70b | DeepSeek | DeepSeek | 3 | 8.2K | 8.2K | Text | Text | Yes | -No | -No | Yes | Open weight | Pricing unavailable | 2025-01-23 | 2025-01-27 | |
| DeepSeek-R1 deepseek/deepseek/r1 | DeepSeek | DeepSeek | 13 | 128K | 33K | Text | Text | Yes | Yes | -No | Yes | Open weight | input $0.574/M output $2.294/M | 2025-01-20 | 2026-02-28 | |
| Qwen-Omni Turbo alibaba/qwen/omni-turbo | Alibaba | Qwen | 3 | 33K | 2K | TextImageAudioVideo | TextAudio | -No | Yes | -No | Yes | Closed | input $0.07/M output $0.27/M | 2025-01-19 | 2025-03-26 | |
| MiniMax-01 minimax/minimax/01 | MiniMax | Minimax | 3 | 1M | 1M | TextImage | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2025-01-15 | 2025-01-15 | |
| Phi 4 microsoft/phi/4 | Microsoft | Phi | 2 | 16K | 16K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2025-01-10 | 2025-01-10 | |
| o3-mini openai/o-series/o3-mini | OpenAI | o-series | 17 | 200K | 100K | Text | Text | Yes | Yes | Yes | -No | Closed | input $1.1/M · cache read $0.55/M output $4.4/M | 2024-12-20 | 2026-01-01 | |
| Llama 3.3 Euryale 70B sao10k/l3/3-euryale-70b | SASao10k | L3 | 2 | 131K | 16K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-12-18 | 2024-12-18 | |
| Gemini 2.0 Flash google/gemini/2-0-flash | Gemini | 3 | 1M | 8.2K | TextImageAudioVideoDocument | Text | -No | Yes | Yes | Yes | Closed | input $0.1/M · cache read $0.025/M output $0.4/M | 2024-12-11 | 2025-08-05 | ||
| Gemini 2.0 Flash-Lite google/gemini/2-0-flash-lite | Gemini | 4 | 1M | 8.2K | TextImageAudioVideoDocument | Text | -No | Yes | Yes | Yes | Closed | input $0.075/M output $0.3/M | 2024-12-11 | 2025-08-05 | ||
| Llama-3.3-70B-Instruct meta/llama/3-3-70b-instruct | Meta | Llama | 17 | 128K | 4.1K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0/M output $0/M | 2024-12-06 | 2026-07-22 | |
| o1 openai/o-series/o1 | OpenAI | o-series | 13 | 200K | 100K | TextImageDocument | Text | Yes | Yes | Yes | -No | Closed | input $15/M · cache read $7.5/M output $60/M | 2024-12-05 | 2025-01-01 | |
| Nova Lite 1.0 amazon/nova/lite-v1 | AMAmazon | Nova | 3 | 300K | 5.1K | TextImage | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2024-12-05 | 2024-12-05 | |
| Nova Micro 1.0 amazon/nova/micro-v1 | AMAmazon | Nova | 3 | 128K | 5.1K | Text | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2024-12-05 | 2024-12-05 | |
| Nova Pro 1.0 amazon/nova/pro-v1 | AMAmazon | Nova | 3 | 300K | 5.1K | TextImage | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2024-12-05 | 2024-12-05 | |
| Command R7B cohere/command/r7b-12-2024 | Cohere | Command | 4 | 128K | 4K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.0375/M output $0.15/M | 2024-12-02 | 2024-12-02 | |
| GPT-4o (2024-11-20) openai/gpt/4o-2024-11-20 | OpenAI | GPT | 7 | 128K | 16K | TextImage | Text | -No | Yes | Yes | Yes | Closed | input $2.5/M · cache read $1.25/M output $10/M | 2024-11-20 | 2024-11-20 | |
| Mistral Large 2407 mistral/mistral/large-2407 | Mistral AI | Mistral | 2 | 131K | - | TextDocument | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2024-11-19 | 2024-11-19 | |
| Mistral Large 2.1 mistral/mistral/large-2411 | Mistral AI | Mistral | 3 | 131K | 16K | Text | Text | -No | Yes | -No | Yes | Open weight | input $2/M output $6/M | 2024-11-18 | 2024-11-18 | |
| Qwen2.5 Coder 32B Instruct alibaba/qwen/2-5-coder-32b-instruct | Alibaba | Qwen | 2 | 33K | 33K | Text | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2024-11-11 | 2024-11-11 | |
| UnslopNemo 12B thedrummer/unslopnemo/12b | THThedrummer | Unslopnemo | 2 | 1M | 1M | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2024-11-08 | 2024-11-08 | |
| Qwen Turbo alibaba/qwen/turbo | Alibaba | Qwen | 4 | 1M | 16K | Text | Text | Yes | Yes | -No | Yes | Closed | input $0.05/M output $0.2/M | 2024-11-01 | 2025-08-05 | |
| Mistral Large 3 mistral/mistral/large-2512 | Mistral AI | Mistral | 8 | 262K | 262K | TextImageDocument | Text | -No | Yes | Yes | Yes | Open weight | input $0.5/M output $1.5/M | 2024-11-01 | 2025-12-16 | |
| Pixtral Large (latest) mistral/pixtral/large-latest | Mistral AI | Pixtral | 2 | 128K | 128K | TextImage | Text | -No | Yes | -No | Yes | Open weight | input $2/M output $6/M | 2024-11-01 | 2024-11-04 | |
| Aya Expanse 32B cohere/aya/c4ai-aya-expanse-32b | Cohere | Aya | 1 | 128K | 4K | Text | Text | -No | -No | -No | Yes | Open weight | input $0.5/M output $1.5/M | 2024-10-24 | 2024-10-24 | |
| Aya Expanse 8B cohere/aya/c4ai-aya-expanse-8b | Cohere | Aya | 1 | 8K | 4K | Text | Text | -No | -No | -No | Yes | Open weight | input $0.5/M output $1.5/M | 2024-10-24 | 2024-10-24 | |
| Claude Haiku 3.5 anthropic/claude/3-5-haiku-20241022 | Anthropic | Claude | 2 | 200K | 8.2K | TextImageDocument | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2024-10-22 | 2024-10-22 | |
| Claude Sonnet 3.5 v2 anthropic/claude/3-5-sonnet-20241022 | Anthropic | Claude | - | 200K | 8.2K | TextImageDocument | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2024-10-22 | 2024-10-22 | |
| Magnum v4 72B anthracite-org/magnum/v4-72b | AOAnthracite Org | Magnum | 3 | 16K | 2K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-10-22 | 2025-01-01 | |
| Qwen2.5 7B Instruct alibaba/qwen/2-5-7b-instruct | Alibaba | Qwen | 2 | 33K | 33K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2024-10-16 | 2024-10-16 | |
| Whisper 3 Large openai/whisper/large-v3 | OpenAI | Whisper | 6 | 448 | 4.1K | Audio | Text | -No | -No | -No | -No | Open weight | input $0/M output $0/M | 2024-10-01 | 2026-03-17 | |
| Whisper Large v3 Turbo openai/whisper/large-v3-turbo | OpenAI | Whisper | 2 | 448 | 448 | Audio | Text | -No | -No | -No | -No | Open weight | Pricing unavailable | 2024-10-01 | 2024-10-01 | |
| Rocinante 12B thedrummer/rocinante/12b | THThedrummer | Rocinante | 2 | 66K | 66K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-09-30 | 2024-09-30 | |
| Llama 3.2 1B Instruct meta/llama/3-2-1b-instruct | Meta | Llama | 2 | 60K | 60K | Text | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2024-09-25 | 2024-09-25 | |
| Llama 3.2 3B Instruct meta/llama/3-2-3b-instruct | Meta | Llama | 4 | 131K | 131K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-09-25 | 2024-09-25 | |
| Qwen2.5 72B Instruct alibaba/qwen/2-5-72b-instruct | Alibaba | Qwen | 4 | 33K | 16K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2024-09-19 | 2025-07-03 | |
| Pixtral 12B mistral/pixtral/12b | Mistral AI | Pixtral | 2 | 128K | 128K | TextImage | Text | -No | Yes | -No | Yes | Open weight | input $0.15/M output $0.15/M | 2024-09-01 | 2024-09-01 | |
| Qwen2.5-VL 72B Instruct alibaba/qwen/qwen2-5-vl-72b-instruct | Alibaba | Qwen | 8 | 131K | 8.2K | TextImage | Text | -No | Yes | Yes | Yes | Open weight | input $2.8/M output $8.4/M | 2024-09 | 2025-08-05 | |
| Command R cohere/command/r-08-2024 | Cohere | Command | 4 | 128K | 4K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.15/M output $0.6/M | 2024-08-30 | 2024-08-30 | |
| Command R+ cohere/command/r-plus-08-2024 | Cohere | Command | 6 | 128K | 4K | Text | Text | -No | Yes | -No | Yes | Open weight | input $2.5/M output $10/M | 2024-08-30 | 2024-08-30 | |
| Llama 3.1 Euryale 70B v2.2 sao10k/l3/1-euryale-70b | SASao10k | L3 | 2 | 131K | 16K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2024-08-28 | 2024-08-28 | |
| Nemotron Mini 4B Instruct nvidia/nemotron/mini-4b-instruct | NVIDIA | Nemotron | 1 | 128K | 8.2K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0/M output $0/M | 2024-08-21 | 2024-08-26 | |
| Hermes 3 70B Instruct nousresearch/hermes/3-llama-3-1-70b | NONousresearch | Hermes | 2 | 131K | 16K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-08-18 | 2024-08-18 | |
| Hermes 3 405B Instruct nousresearch/hermes/3-llama-3-1-405b | NONousresearch | Hermes | 2 | 131K | 16K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-08-16 | 2024-08-16 | |
| Llama 3 8B Lunaris sao10k/l3/lunaris-8b | SASao10k | L3 | 2 | 8.2K | 16K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-08-13 | 2024-08-13 | |
| GPT-4o (2024-08-06) openai/gpt/4o-2024-08-06 | OpenAI | GPT | 6 | 128K | 16K | TextImage | Text | -No | Yes | Yes | Yes | Closed | input $2.5/M · cache read $1.25/M output $10/M | 2024-08-06 | 2024-08-06 | |
| Llama 3.1 70B Instruct meta/llama/3-1-70b-instruct | Meta | Llama | 2 | 131K | 16K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2024-07-23 | 2024-07-23 | |
| Llama 3.1 8B Instruct meta/llama/3-1-8b-instruct | Meta | Llama | 4 | 131K | 131K | Text | Text | -No | Yes | Yes | Yes | Open weight | Pricing unavailable | 2024-07-23 | 2024-07-24 | |
| GPT-4o mini openai/gpt/4o-mini | OpenAI | GPT | 18 | 128K | 16K | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | input $0.15/M · cache read $0.075/M output $0.6/M | 2024-07-18 | 2024-07-18 | |
| GPT-4o-mini (2024-07-18) openai/gpt/4o-mini-2024-07-18 | OpenAI | GPT | 2 | 128K | 16K | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2024-07-18 | 2024-07-18 | |
| Gemma 2 27B google/gemma/2-27b-it | Gemma | 2 | 8.2K | 2K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2024-07-13 | 2024-07-13 | ||
| Mistral Nemo mistral/mistral/nemo | Mistral AI | Mistral | 6 | 128K | 128K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.15/M output $0.15/M | 2024-07-01 | 2024-07-30 | |
| o3-deep-research openai/o-series/o3-deep-research | OpenAI | o-series | 4 | 200K | 100K | TextImage | Text | Yes | Yes | -No | -No | Closed | Pricing unavailable | 2024-06-26 | 2025-06-27 | |
| o4-mini-deep-research openai/o-series/o4-mini-deep-research | OpenAI | o-series | 3 | 200K | 100K | TextImage | Text | Yes | Yes | -No | -No | Closed | Pricing unavailable | 2024-06-26 | 2025-06-27 | |
| Codestral (latest) mistral/codestral/latest | Mistral AI | Codestral | 2 | 256K | 4.1K | Text | Text | -No | Yes | -No | Yes | Open weight | input $0.3/M output $0.9/M | 2024-05-29 | 2025-01-04 | |
| GPT-4o openai/gpt/4o | OpenAI | GPT | 18 | 128K | 16K | TextImageDocument | Text | -No | Yes | Yes | Yes | Closed | input $2.5/M · cache read $1.25/M output $10/M | 2024-05-13 | 2024-08-06 | |
| GPT-4o (2024-05-13) openai/gpt/4o-2024-05-13 | OpenAI | GPT | 5 | 128K | 4.1K | TextImage | Text | -No | Yes | Yes | Yes | Closed | input $5/M output $15/M | 2024-05-13 | 2024-05-13 | |
| Mixtral 8x22B Instruct mistral/mixtral/8x22b-instruct | Mistral AI | Mixtral | 3 | 66K | - | TextDocument | Text | -No | Yes | Yes | Yes | Open weight | input $0/M output $0/M | 2024-04-17 | 2024-04-17 | |
| WizardLM-2 8x22B microsoft/wizardlm/2-8x22b | Microsoft | Wizardlm | 4 | 66K | 8K | Text | Text | -No | -No | -No | Yes | Open weight | Pricing unavailable | 2024-04-16 | 2025-04-15 | |
| Qwen-VL Max alibaba/qwen/vl-max | Alibaba | Qwen | 2 | 131K | 8.2K | TextImage | Text | -No | Yes | -No | Yes | Closed | input $0.8/M output $3.2/M | 2024-04-08 | 2025-08-13 | |
| Qwen Max alibaba/qwen/max | Alibaba | Qwen | 4 | 33K | 8.2K | Text | Text | -No | Yes | -No | Yes | Closed | input $1.6/M output $6.4/M | 2024-04-03 | 2025-01-25 | |
| Claude Haiku 3 anthropic/claude/3-haiku-20240307 | Anthropic | Claude | 1 | 200K | 4.1K | TextImageDocument | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2024-03-13 | 2024-03-13 | |
| Claude 3 Haiku anthropic/claude/3-haiku | Anthropic | Claude | 4 | 200K | 4.1K | TextImage | Text | -No | Yes | -No | Yes | Closed | Pricing unavailable | 2024-03-13 | 2024-03-13 | |
| Mistral Large mistral/mistral/large | Mistral AI | Mistral | 6 | 128K | - | TextImageDocument | Text | -No | Yes | Yes | Yes | Open weight | input $0.5/M output $1.5/M | 2024-02-26 | 2025-12-02 | |
| Qwen Plus alibaba/qwen/plus | Alibaba | Qwen | 8 | 1M | 33K | Text | Text | Yes | Yes | Yes | Yes | Closed | input $0.4/M output $1.2/M | 2024-01-25 | 2025-09-11 | |
| Qwen-VL Plus alibaba/qwen/vl-plus | Alibaba | Qwen | 2 | 131K | 8.2K | TextImage | Text | -No | Yes | -No | Yes | Closed | input $0.21/M output $0.63/M | 2024-01-25 | 2025-08-15 | |
| GPT-3.5 Turbo (older v0613) openai/gpt/3-5-turbo-0613 | OpenAI | GPT | 2 | 4.1K | 4.1K | Text | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2024-01-25 | 2024-01-25 | |
| GPT-4 Turbo Preview openai/gpt/4-turbo-preview | OpenAI | GPT | 3 | 128K | 4.1K | Text | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2024-01-25 | 2024-01-25 | |
| Sonar perplexity/sonar/sonar | Perplexity | Sonar | 9 | 128K | 4.1K | Text | Text | -No | -No | -No | Yes | Closed | input $1/M output $1/M | 2024-01-01 | 2025-09-01 | |
| Sonar Pro perplexity/sonar/pro | Perplexity | Sonar | 9 | 200K | 8.2K | TextImage | Text | -No | -No | -No | Yes | Closed | input $3/M output $15/M | 2024-01-01 | 2025-09-01 | |
| Sonar Reasoning Pro perplexity/sonar/reasoning-pro | Perplexity | Sonar | 8 | 128K | 4.1K | TextImage | Text | Yes | -No | -No | Yes | Closed | input $2/M output $8/M | 2024-01-01 | 2025-09-01 | |
| GPT-4 openai/gpt/4 | OpenAI | GPT | 7 | 8.2K | 8.2K | Text | Text | -No | Yes | -No | Yes | Closed | input $30/M output $60/M | 2023-11-06 | 2024-04-09 | |
| GPT-4 Turbo openai/gpt/4-turbo | OpenAI | GPT | 12 | 128K | 4.1K | TextImage | Text | -No | Yes | -No | Yes | Closed | input $10/M output $30/M | 2023-11-06 | 2024-04-09 | |
| GPT-3.5 Turbo Instruct openai/gpt/3-5-turbo-instruct | OpenAI | GPT | 3 | 4.1K | 4.1K | Text | Text | -No | -No | Yes | Yes | Closed | Pricing unavailable | 2023-09-28 | 2023-09-28 | |
| GPT-3.5 Turbo 16k openai/gpt/3-5-turbo-16k | OpenAI | GPT | 2 | 16K | 4.1K | Text | Text | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2023-08-28 | 2023-08-28 | |
| Weaver (alpha) mancer/weaver/weaver | MAMancer | Weaver | 2 | 8K | 2K | Text | Text | -No | -No | Yes | Yes | Closed | Pricing unavailable | 2023-08-02 | 2023-08-02 | |
| ReMM SLERP 13B undi95/remm/slerp-l2-13b | UNUndi95 | Remm | 3 | 6.1K | 2K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2023-07-22 | 2025-01-01 | |
| MythoMax 13B gryphe/mythomax/l2-13b | GRGryphe | Mythomax | 3 | 8.2K | 4.1K | Text | Text | -No | -No | Yes | Yes | Open weight | Pricing unavailable | 2023-07-02 | 2024-04-25 | |
| GPT-3.5-turbo openai/gpt/3-5-turbo | OpenAI | GPT | 10 | 16K | 4.1K | Text | Text | -No | -No | -No | Yes | Closed | input $0.5/M · cache read $0/M output $1.5/M | 2023-03-01 | 2023-11-06 |