← All providers
LLM Gateway
371 models · routes through the OpenAI-Compatible adapter
API endpoint
https://api.llmgateway.io/v1
Required environment variables
- LLMGATEWAY_API_KEY
Models
| Model | Context | Input | Output | Capabilities |
|---|---|---|---|---|
| zai/glm-5.3 | 1000k | $1.40 / 1M | $4.40 / 1M | tools, reasoning |
| google-ai-studio/gemini-3.7-flash | 1049k | $0.75 / 1M | $3.75 / 1M | tools, reasoning, vision |
| google-vertex/gemini-3.7-flash | 1049k | $0.75 / 1M | $3.75 / 1M | tools, reasoning, vision |
| aws-bedrock/grok-4-6 | 500k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, vision |
| vertex-openai/grok-4-6 | 500k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, vision |
| xai/grok-4-6 | 500k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, vision |
| meta/muse-spark-1.2 | 1049k | $1.25 / 1M | $4.25 / 1M | tools, reasoning, vision |
| alibaba/qwen3.8-max | 1000k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, vision |
| novita/qwen3.8-max | 1000k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, vision |
| scx-ai-gp/qwen3.8-max | 1000k | $1.81 / 1M | $5.45 / 1M | tools, reasoning, vision |
| deepinfra/ling-3.0-flash | 262k | $0.06 / 1M | $0.18 / 1M | tools, reasoning |
| novita/ling-3.0-flash | 262k | $0.06 / 1M | $0.18 / 1M | tools, reasoning |
| anthropic/claude-opus-5 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-opus-5 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| google-ai-studio/gemini-3.5-flash-lite | 1049k | $0.30 / 1M | $2.50 / 1M | tools, reasoning, vision |
| google-ai-studio/gemini-3.6-flash | 1049k | $0.75 / 1M | $3.75 / 1M | tools, reasoning, vision |
| google-vertex/gemini-3.5-flash-lite | 1049k | $0.30 / 1M | $2.50 / 1M | tools, reasoning, vision |
| google-vertex/gemini-3.6-flash | 1049k | $0.75 / 1M | $3.75 / 1M | tools, reasoning, vision |
| iceberg/gemini-3.6-flash | 1049k | $0.75 / 1M | $3.75 / 1M | tools, reasoning, vision |
| canopywave/kimi-k3 | 1049k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| fireworks/kimi-k3 | 1040k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| fireworks/kimi-k3-fast | 1040k | $4.50 / 1M | $22.50 / 1M | tools, reasoning, open-weights, vision |
| moonshot/kimi-k3 | 1049k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| nebius/kimi-k3 | 1049k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| novita/kimi-k3 | 1049k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| permafrost/kimi-k3 | 1049k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| together-ai/kimi-k3 | 1000k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, open-weights, vision |
| alibaba/qwen3.7-flash | 1000k | $0.03 / 1M | $0.13 / 1M | tools, reasoning, vision |
| aws-mantle/gpt-5.6-luna | 279k | $0.22 / 1M | $1.32 / 1M | tools, reasoning, vision |
| aws-mantle/gpt-5.6-sol | 279k | $5.50 / 1M | $33.00 / 1M | tools, reasoning, vision |
| aws-mantle/gpt-5.6-terra | 279k | $2.20 / 1M | $13.20 / 1M | tools, reasoning, vision |
| azure/gpt-5.6-luna | 1050k | $0.20 / 1M | $1.20 / 1M | tools, reasoning, vision |
| azure/gpt-5.6-sol | 1050k | $5.00 / 1M | $30.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.6-terra | 1050k | $2.00 / 1M | $12.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.6-luna | 1050k | $0.20 / 1M | $1.20 / 1M | tools, reasoning, vision |
| openai/gpt-5.6-sol | 1050k | $5.00 / 1M | $30.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.6-terra | 1050k | $2.00 / 1M | $12.00 / 1M | tools, reasoning, vision |
| xai/grok-4-5 | 500k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, vision |
| deepinfra/hy3 | 262k | $0.14 / 1M | $0.58 / 1M | tools, reasoning, open-weights |
| novita/hy3 | 262k | $0.14 / 1M | $0.58 / 1M | tools, reasoning, open-weights |
| anthropic/claude-sonnet-5 | 1000k | $2.00 / 1M | $10.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-sonnet-5 | 1000k | $2.00 / 1M | $10.00 / 1M | tools, reasoning, vision |
| vertex-anthropic/claude-sonnet-5 | 1000k | $2.00 / 1M | $10.00 / 1M | tools, reasoning, vision |
| sakana/fugu-ultra | 1000k | $5.00 / 1M | $30.00 / 1M | tools, reasoning, vision |
| alibaba/glm-5.2 | 1000k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| baidu/glm-5.2 | 1049k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| bytedance/glm-5.2 | 1024k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| canopywave/glm-5.2 | 200k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| embercloud/glm-5.2 | 203k | $1.26 / 1M | $3.96 / 1M | tools, reasoning, open-weights |
| nebius/glm-5.2 | 1049k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| novita/glm-5.2 | 1049k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| runware/glm-5.2 | 1024k | $0.80 / 1M | $2.55 / 1M | tools, reasoning, open-weights |
| scx-ai-gp/glm-5.2 | 1000k | $0.55 / 1M | $1.78 / 1M | tools, reasoning, open-weights |
| scx-ai-gp/glm-5.2-fast | 1000k | $1.99 / 1M | $6.16 / 1M | tools, reasoning, open-weights |
| zai/glm-5.2 | 1000k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| moonshot/kimi-k2.7-code | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights, vision |
| moonshot/kimi-k2.7-code-highspeed | 262k | $1.90 / 1M | $8.00 / 1M | tools, reasoning, open-weights, vision |
| nebius/kimi-k2.7-code | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights |
| novita/kimi-k2.7-code | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights, vision |
| anthropic/claude-fable-5 | 1000k | $10.00 / 1M | $50.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-fable-5 | 1000k | $10.00 / 1M | $50.00 / 1M | tools, reasoning, vision |
| alibaba/qwen3.7-plus | 1000k | $0.40 / 1M | $1.60 / 1M | tools, reasoning, vision |
| deepinfra/nemotron-3-ultra-550b | 262k | $0.50 / 1M | $2.20 / 1M | tools, vision |
| minimax/minimax-m3 | 512k | $0.60 / 1M | $2.40 / 1M | tools, reasoning, open-weights, vision |
| nebius/cosmos3-super-reasoner | 262k | $0.10 / 1M | $0.30 / 1M | tools, reasoning, vision |
| nebius/minimax-m3 | 1049k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| nebius/nemotron-3-ultra-550b | 1049k | $1.00 / 1M | $3.00 / 1M | tools, reasoning |
| together-ai/minimax-m3 | 524k | $0.30 / 1M | $1.20 / 1M | reasoning, open-weights |
| anthropic/claude-opus-4-8 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-opus-4-8 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| alibaba/qwen3.7-max | 1000k | $2.50 / 1M | $7.50 / 1M | tools, reasoning |
| novita/qwen3.7-max | 1000k | $1.25 / 1M | $3.75 / 1M | tools, reasoning |
| xai/grok-build-0-1 | 256k | $1.00 / 1M | $2.00 / 1M | tools, reasoning, vision |
| google-ai-studio/gemini-3.5-flash | 1049k | $1.50 / 1M | $9.00 / 1M | tools, reasoning, vision |
| google-vertex/gemini-3.5-flash | 1049k | $1.50 / 1M | $9.00 / 1M | tools, reasoning, vision |
| google-ai-studio/gemini-3.1-flash-lite | 1049k | $0.25 / 1M | $1.50 / 1M | tools, reasoning, vision |
| google-vertex/gemini-3.1-flash-lite | 1049k | $0.25 / 1M | $1.50 / 1M | tools, reasoning, vision |
| aws-bedrock/grok-4-3 | 1000k | $1.25 / 1M | $2.50 / 1M | tools, reasoning, vision |
| azure-ai-foundry/grok-4-3 | 20k | $1.25 / 1M | $2.50 / 1M | tools, reasoning |
| xai/grok-4-3 | 1000k | $1.25 / 1M | $2.50 / 1M | tools, reasoning, vision |
| nebius/nemotron-3-nano-omni | 262k | $0.06 / 1M | $0.24 / 1M | tools, reasoning, vision |
| alibaba/qwen3.6-flash | 1000k | $0.25 / 1M | $1.50 / 1M | tools, reasoning, vision |
| alibaba/deepseek-v4-flash | 1000k | $0.20 / 1M | $0.40 / 1M | tools, reasoning, open-weights |
| alibaba/deepseek-v4-pro | 1000k | $2.40 / 1M | $4.80 / 1M | tools, reasoning, open-weights |
| baidu/deepseek-v4-flash | 1049k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| baidu/deepseek-v4-pro | 1049k | $1.69 / 1M | $3.38 / 1M | tools, reasoning, open-weights |
| bytedance/deepseek-v4-flash | 1049k | $0.44 / 1M | $1.32 / 1M | tools, reasoning, open-weights |
| bytedance/deepseek-v4-pro | 1049k | $1.32 / 1M | $3.96 / 1M | tools, reasoning, open-weights |
| canopywave/deepseek-v4-flash | 1000k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| canopywave/deepseek-v4-pro | 1000k | $1.74 / 1M | $3.48 / 1M | tools, reasoning, open-weights |
| deepinfra/deepseek-v4-flash | 1000k | $0.08 / 1M | $0.18 / 1M | tools, reasoning, open-weights |
| deepinfra/deepseek-v4-pro | 1049k | $1.30 / 1M | $2.60 / 1M | tools, reasoning, open-weights |
| deepseek/deepseek-v4-flash | 1050k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| deepseek/deepseek-v4-pro | 1050k | $0.43 / 1M | $0.87 / 1M | tools, reasoning, open-weights |
| fireworks/deepseek-v4-flash | 1049k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| fireworks/deepseek-v4-pro | 1049k | $1.32 / 1M | $3.96 / 1M | tools, reasoning, open-weights |
| gonka24/deepseek-v4-flash | 390k | $0.07 / 1M | $0.17 / 1M | tools, reasoning, open-weights |
| nebius/deepseek-v4-pro | 1049k | $1.75 / 1M | $3.50 / 1M | tools, reasoning, open-weights |
| novita/deepseek-v4-flash | 1050k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| ranoai/deepseek-v4-flash | 1000k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| runware/deepseek-v4-flash | 1049k | $0.08 / 1M | $0.15 / 1M | tools, reasoning, open-weights |
| runware/deepseek-v4-pro | 1049k | $0.96 / 1M | $1.92 / 1M | tools, reasoning, open-weights |
| together-ai/deepseek-v4-flash | 164k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights |
| together-ai/deepseek-v4-pro | 1049k | $1.32 / 1M | $3.96 / 1M | tools, reasoning, open-weights |
| azure/gpt-5.5 | 1050k | $5.00 / 1M | $30.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.5 | 1050k | $5.00 / 1M | $30.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.5-pro | 1050k | $30.00 / 1M | $180.00 / 1M | tools, reasoning, vision |
| deepinfra/mimo-v2.5 | 262k | $0.40 / 1M | $2.00 / 1M | tools, reasoning, open-weights, vision |
| deepinfra/mimo-v2.5-pro | 1049k | $1.00 / 1M | $3.00 / 1M | reasoning, open-weights |
| novita/mimo-v2.5 | 1049k | $0.17 / 1M | $0.34 / 1M | tools, reasoning, open-weights, vision |
| novita/mimo-v2.5-pro | 1049k | $0.52 / 1M | $1.04 / 1M | tools, reasoning, open-weights |
| xiaomi/mimo-v2.5 | 1000k | $0.14 / 1M | $0.28 / 1M | tools, reasoning, open-weights, vision |
| xiaomi/mimo-v2.5-pro | 1000k | $0.43 / 1M | $0.87 / 1M | tools, reasoning, open-weights |
| baidu/kimi-k2.6 | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights, vision |
| canopywave/kimi-k2.6 | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights, vision |
| gonka24/kimi-k2.6 | 262k | $0.22 / 1M | $1.14 / 1M | tools, reasoning, open-weights |
| moonshot/kimi-k2.6 | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights, vision |
| nebius/kimi-k2.6 | 262k | $0.95 / 1M | $4.00 / 1M | tools, reasoning, open-weights, vision |
| novita/kimi-k2.6 | 262k | $0.80 / 1M | $3.40 / 1M | tools, reasoning, open-weights, vision |
| runware/kimi-k2.6 | 262k | $0.60 / 1M | $3.05 / 1M | tools, reasoning, open-weights, vision |
| tundra/kimi-k2.6 | 262k | $0.40 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| alibaba/qwen3.6-max-preview | 262k | $1.30 / 1M | $7.80 / 1M | tools, reasoning |
| alibaba/qwen3.6-35b-a3b | 262k | $0.25 / 1M | $1.49 / 1M | tools, reasoning, open-weights, vision |
| novita/qwen3.6-35b-a3b | 262k | $0.25 / 1M | $1.49 / 1M | tools, reasoning, open-weights, vision |
| anthropic/claude-opus-4-7 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-opus-4-7 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| vertex-anthropic/claude-opus-4-7 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| meta/muse-spark-1.1 | 1049k | $1.25 / 1M | $4.25 / 1M | tools, reasoning, vision |
| baidu/glm-5.1 | 203k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| deepinfra/glm-5.1 | 198k | $1.05 / 1M | $3.50 / 1M | tools, reasoning, open-weights |
| embercloud/glm-5.1 | 203k | $0.93 / 1M | $2.93 / 1M | tools, reasoning, open-weights |
| nebius/glm-5.1 | 203k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| novita/glm-5.1 | 205k | $1.38 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| zai/glm-5.1 | 200k | $1.40 / 1M | $4.40 / 1M | tools, reasoning, open-weights |
| alibaba/qwen3.6-plus | 262k | $0.50 / 1M | $3.00 / 1M | tools, reasoning, vision |
| cerebras/gemma-4-31b-it | 131k | $0.99 / 1M | $1.49 / 1M | tools, reasoning, open-weights, vision |
| deepinfra/gemma-4-26b-a4b-it | 262k | $0.07 / 1M | $0.34 / 1M | tools, reasoning, open-weights |
| deepinfra/gemma-4-31b-it | 262k | $0.13 / 1M | $0.38 / 1M | tools, reasoning, open-weights |
| novita/gemma-4-26b-a4b-it | 262k | $0.13 / 1M | $0.40 / 1M | tools, open-weights |
| novita/gemma-4-31b-it | 262k | $0.14 / 1M | $0.40 / 1M | tools, open-weights |
| runware/gemma-4-31b-it | 262k | $0.10 / 1M | $0.30 / 1M | tools, reasoning, open-weights, vision |
| scx-ai/gemma-4-31b-it | 131k | $0.30 / 1M | $0.91 / 1M | tools, open-weights |
| together-ai/gemma-4-31b-it | 262k | $0.39 / 1M | $0.97 / 1M | tools, reasoning, open-weights |
| gonka24/minimax-m2.7 | 205k | $0.08 / 1M | $0.32 / 1M | tools, reasoning, open-weights |
| minimax/minimax-m2.7 | 205k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| minimax/minimax-m2.7-highspeed | 205k | $0.60 / 1M | $2.40 / 1M | tools, reasoning, open-weights |
| novita/minimax-m2.7 | 205k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| scx-ai/minimax-m2.7 | 197k | $0.48 / 1M | $1.79 / 1M | tools, reasoning, open-weights |
| azure/gpt-5.4-mini | 400k | $0.75 / 1M | $4.50 / 1M | tools, reasoning, vision |
| azure/gpt-5.4-nano | 400k | $0.20 / 1M | $1.25 / 1M | tools, reasoning, vision |
| openai/gpt-5.4-mini | 400k | $0.75 / 1M | $4.50 / 1M | tools, reasoning, vision |
| openai/gpt-5.4-nano | 400k | $0.20 / 1M | $1.25 / 1M | tools, reasoning, vision |
| nebius/nemotron-3-super-120b | 262k | $0.30 / 1M | $0.90 / 1M | tools, reasoning |
| vertex-openai/grok-4-20-non-reasoning | 2000k | $1.25 / 1M | $2.50 / 1M | tools, vision |
| vertex-openai/grok-4-20-reasoning | 2000k | $1.25 / 1M | $2.50 / 1M | tools, reasoning, vision |
| xai/grok-4-20-beta-0309-non-reasoning | 2000k | $2.00 / 1M | $6.00 / 1M | tools, vision |
| xai/grok-4-20-beta-0309-reasoning | 2000k | $2.00 / 1M | $6.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.4 | 1050k | $2.50 / 1M | $15.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.4-pro | 1050k | $30.00 / 1M | $180.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.4 | 1050k | $2.50 / 1M | $15.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.4-pro | 1050k | $30.00 / 1M | $180.00 / 1M | tools, reasoning, vision |
| google-ai-studio/gemini-pro-latest | 1049k | $2.00 / 1M | $12.00 / 1M | tools, reasoning, vision |
| deepinfra/qwen3.5-9b | 262k | $0.10 / 1M | $0.15 / 1M | tools, reasoning, open-weights |
| google-ai-studio/gemini-3.1-pro-preview | 1049k | $2.00 / 1M | $12.00 / 1M | tools, reasoning, vision |
| google-vertex/gemini-3.1-pro-preview | 1049k | $2.00 / 1M | $12.00 / 1M | tools, reasoning, vision |
| iceberg/gemini-3.1-pro-preview | 1049k | $2.00 / 1M | $12.00 / 1M | tools, reasoning, vision |
| quartz/gemini-3.1-pro-preview | 1049k | $2.00 / 1M | $12.00 / 1M | tools, reasoning, vision |
| anthropic/claude-sonnet-4-6 | 1000k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-sonnet-4-6 | 1000k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| vertex-anthropic/claude-sonnet-4-6 | 1000k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| alibaba/qwen35-397b-a17b | 262k | $0.60 / 1M | $3.60 / 1M | tools, reasoning, vision |
| novita/qwen35-397b-a17b | 262k | $0.60 / 1M | $3.60 / 1M | tools, reasoning, vision |
| minimax/minimax-m2.5-highspeed | 205k | $0.60 / 1M | $2.40 / 1M | tools, reasoning, open-weights |
| alibaba/glm-5 | 203k | $0.57 / 1M | $2.58 / 1M | tools, reasoning, open-weights |
| baidu/glm-5 | 203k | $1.00 / 1M | $3.20 / 1M | tools, reasoning, open-weights |
| embercloud/glm-5 | 203k | $0.72 / 1M | $2.30 / 1M | tools, reasoning, open-weights |
| minimax/minimax-m2.5 | 205k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| nebius/minimax-m2.5 | 197k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| novita/glm-5 | 203k | $1.00 / 1M | $3.20 / 1M | tools, reasoning, open-weights |
| novita/minimax-m2.5 | 205k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| vertex-openai/glm-5 | 203k | $1.00 / 1M | $3.20 / 1M | tools, reasoning, open-weights |
| zai/glm-5 | 203k | $1.00 / 1M | $3.20 / 1M | tools, reasoning, open-weights |
| anthropic/claude-opus-4-6 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-opus-4-6 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.3-codex | 400k | $1.75 / 1M | $14.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.3-codex | 400k | $1.75 / 1M | $14.00 / 1M | tools, reasoning, vision |
| vertex-anthropic/claude-opus-4-6 | 1000k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| embercloud/qwen3-coder-next | 262k | $0.11 / 1M | $0.68 / 1M | tools, open-weights |
| embercloud/glm-4.7-flash | 200k | $0.06 / 1M | $0.40 / 1M | tools, open-weights |
| zai/glm-4.7-flashx | 200k | $0.07 / 1M | $0.40 / 1M | tools, reasoning, open-weights |
| alibaba/kimi-k2.5 | 262k | $0.57 / 1M | $3.01 / 1M | tools, reasoning, open-weights, vision |
| deepinfra/kimi-k2.5 | 256k | $0.45 / 1M | $2.25 / 1M | tools, reasoning, open-weights, vision |
| embercloud/kimi-k2.5 | 262k | $0.41 / 1M | $1.98 / 1M | tools, open-weights |
| moonshot/kimi-k2.5 | 262k | $0.60 / 1M | $3.00 / 1M | tools, reasoning, open-weights, vision |
| minimax/minimax-m2.1 | 197k | $0.27 / 1M | $1.10 / 1M | tools, reasoning, open-weights |
| minimax/minimax-m2.1-lightning | 197k | $0.12 / 1M | $0.48 / 1M | tools, reasoning |
| novita/minimax-m2.1 | 205k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| bytedance/glm-4.7 | 200k | $0.60 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| cerebras/glm-4.7 | 200k | $2.25 / 1M | $2.75 / 1M | tools, reasoning, open-weights |
| embercloud/glm-4.7 | 200k | $0.38 / 1M | $1.98 / 1M | tools, reasoning, open-weights |
| novita/glm-4.7 | 205k | $0.60 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| together-ai/glm-4.7 | 203k | $0.45 / 1M | $2.00 / 1M | reasoning, open-weights |
| vertex-openai/glm-4.7 | 203k | $0.60 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| zai/glm-4.7 | 200k | $0.60 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| bytedance/seed-1-8-251228 | 256k | $0.25 / 1M | $2.00 / 1M | tools, reasoning, vision |
| google-ai-studio/gemini-3-flash-preview | 1049k | $0.50 / 1M | $3.00 / 1M | tools, reasoning, vision |
| google-vertex/gemini-3-flash-preview | 1049k | $0.50 / 1M | $3.00 / 1M | tools, reasoning, vision |
| iceberg/gemini-3-flash-preview | 1049k | $0.50 / 1M | $3.00 / 1M | tools, reasoning, vision |
| nebius/nemotron-3-nano-30b | 262k | $0.06 / 1M | $0.24 / 1M | tools, reasoning |
| azure/gpt-5.2 | 400k | $1.75 / 1M | $14.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.2-codex | 400k | $1.75 / 1M | $14.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.2-pro | 400k | $21.00 / 1M | $168.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.2 | 400k | $1.75 / 1M | $14.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.2-pro | 400k | $21.00 / 1M | $168.00 / 1M | tools, reasoning, vision |
| mistral/devstral-2512 | 262k | $0.40 / 1M | $2.00 / 1M | open-weights |
| novita/glm-4.6v | 131k | $0.30 / 1M | $0.90 / 1M | tools, reasoning, open-weights, vision |
| zai/glm-4.6v | 128k | $0.30 / 1M | $0.90 / 1M | tools, reasoning, open-weights, vision |
| zai/glm-4.6v-flashx | 128k | $0.04 / 1M | $0.40 / 1M | tools, reasoning, vision |
| mistral/ministral-14b-2512 | 262k | $0.20 / 1M | $0.20 / 1M | vision |
| mistral/ministral-3b-2512 | 131k | $0.10 / 1M | $0.10 / 1M | vision |
| mistral/ministral-8b-2512 | 262k | $0.15 / 1M | $0.15 / 1M | vision |
| bytedance/deepseek-v3.2 | 131k | $0.28 / 1M | $0.42 / 1M | tools, reasoning, open-weights |
| deepinfra/deepseek-v3.2 | 160k | $0.26 / 1M | $0.38 / 1M | tools, open-weights |
| novita/deepseek-v3.2 | 164k | $0.27 / 1M | $0.40 / 1M | tools, reasoning, open-weights |
| vertex-openai/deepseek-v3.2 | 164k | $0.56 / 1M | $1.68 / 1M | tools, open-weights |
| azure-ai-foundry/grok-4-1-fast-non-reasoning | 2000k | $0.20 / 1M | $0.50 / 1M | tools, vision |
| azure-ai-foundry/grok-4-1-fast-reasoning | 2000k | $0.20 / 1M | $0.50 / 1M | tools, reasoning, vision |
| azure/gpt-5.1 | 400k | $1.25 / 1M | $10.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.1-codex | 400k | $1.25 / 1M | $10.00 / 1M | tools, reasoning, vision |
| azure/gpt-5.1-codex-mini | 400k | $0.25 / 1M | $2.00 / 1M | tools, reasoning, vision |
| openai/gpt-5.1 | 400k | $1.25 / 1M | $10.00 / 1M | tools, reasoning, vision |
| vertex-openai/kimi-k2-thinking | 262k | $0.60 / 1M | $2.50 / 1M | tools, reasoning, open-weights |
| anthropic/claude-opus-4-5-20251101 | 200k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-opus-4-5-20251101 | 200k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| vertex-anthropic/claude-opus-4-5-20251101 | 200k | $5.00 / 1M | $25.00 / 1M | tools, reasoning, vision |
| minimax/minimax-m2 | 197k | $0.20 / 1M | $1.00 / 1M | tools, reasoning, open-weights |
| alibaba/qwen3-vl-flash | 262k | $0.05 / 1M | $0.40 / 1M | tools, vision |
| anthropic/claude-haiku-4-5 | 200k | $1.00 / 1M | $5.00 / 1M | tools, reasoning, vision |
| anthropic/claude-haiku-4-5-20251001 | 200k | $1.00 / 1M | $5.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-haiku-4-5 | 200k | $1.00 / 1M | $5.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-haiku-4-5-20251001 | 200k | $1.00 / 1M | $5.00 / 1M | tools, reasoning, vision |
| vertex-anthropic/claude-haiku-4-5 | 200k | $1.00 / 1M | $5.00 / 1M | tools, reasoning, vision |
| openai/gpt-5-pro | 400k | $15.00 / 1M | $120.00 / 1M | tools, reasoning, vision |
| deepinfra/qwen3-vl-30b-a3b-instruct | 262k | $0.15 / 1M | $0.60 / 1M | tools, vision |
| novita/qwen3-vl-30b-a3b-instruct | 131k | $0.20 / 1M | $0.70 / 1M | tools, vision |
| novita/glm-4.6 | 205k | $0.55 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| zai/glm-4.6 | 200k | $0.60 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| anthropic/claude-sonnet-4-5 | 200k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| anthropic/claude-sonnet-4-5-20250929 | 200k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-sonnet-4-5 | 200k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| aws-bedrock/claude-sonnet-4-5-20250929 | 200k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| vertex-anthropic/claude-sonnet-4-5 | 200k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| alibaba/qwen3-max | 256k | $3.00 / 1M | $15.00 / 1M | tools, reasoning |
| alibaba/qwen3-vl-plus | 262k | $0.20 / 1M | $1.60 / 1M | vision |
| deepinfra/qwen3-vl-235b-a22b-instruct | 262k | $0.20 / 1M | $0.88 / 1M | tools, open-weights, vision |
| novita/qwen3-max | 262k | $0.84 / 1M | $3.38 / 1M | tools |
| novita/qwen3-vl-235b-a22b-instruct | 131k | $0.30 / 1M | $1.50 / 1M | tools, open-weights, vision |
| novita/qwen3-vl-235b-a22b-thinking | 131k | $0.98 / 1M | $3.95 / 1M | reasoning, open-weights, vision |
| bytedance/seed-1-6-250915 | 256k | $0.25 / 1M | $2.00 / 1M | tools, reasoning, vision |
| nebius/qwen3-next-80b-a3b-thinking | 131k | $0.15 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| novita/qwen3-next-80b-a3b-instruct | 131k | $0.15 / 1M | $1.50 / 1M | tools, open-weights |
| vertex-openai/qwen3-next-80b-a3b-instruct | 131k | $0.15 / 1M | $1.20 / 1M | tools, open-weights |
| vertex-openai/qwen3-next-80b-a3b-thinking | 131k | $0.15 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| nebius/hermes-4-405b | 131k | $1.00 / 1M | $3.00 / 1M | tools, reasoning |
| nebius/hermes-4-70b | 131k | $0.13 / 1M | $0.40 / 1M | tools, reasoning |
| nebius/minicpm-v-4.5 | 32k | $0.66 / 1M | $1.11 / 1M | vision |
| novita/glm-4.5v | 66k | $0.60 / 1M | $1.80 / 1M | tools, reasoning, open-weights, vision |
| zai/glm-4.5v | 128k | $0.60 / 1M | $1.80 / 1M | tools, reasoning, open-weights, vision |
| azure/gpt-5 | 400k | $1.25 / 1M | $10.00 / 1M | tools, reasoning, vision |
| azure/gpt-5-mini | 400k | $0.25 / 1M | $2.00 / 1M | tools, reasoning, vision |
| azure/gpt-5-nano | 400k | $0.05 / 1M | $0.40 / 1M | tools, reasoning |
| openai/gpt-5 | 400k | $1.25 / 1M | $10.00 / 1M | tools, reasoning, vision |
| openai/gpt-5-mini | 400k | $0.25 / 1M | $2.00 / 1M | tools, reasoning, vision |
| openai/gpt-5-nano | 400k | $0.05 / 1M | $0.40 / 1M | tools, reasoning |
| aws-bedrock/claude-opus-4-1-20250805 | 200k | $15.00 / 1M | $75.00 / 1M | tools, reasoning, vision |
| azure/gpt-oss-120b | 131k | $0.15 / 1M | $0.60 / 1M | tools, reasoning, open-weights |
| bytedance/gpt-oss-120b | 128k | $0.10 / 1M | $0.50 / 1M | tools, reasoning, open-weights |
| cerebras/gpt-oss-120b | 131k | $0.35 / 1M | $0.75 / 1M | tools, reasoning, open-weights |
| groq/gpt-oss-120b | 131k | $0.15 / 1M | $0.75 / 1M | tools, reasoning, open-weights |
| groq/gpt-oss-20b | 131k | $0.10 / 1M | $0.50 / 1M | tools, reasoning, open-weights |
| nebius/gpt-oss-120b | 131k | $0.15 / 1M | $0.60 / 1M | tools, reasoning, open-weights |
| runware/gpt-oss-120b | 131k | $0.03 / 1M | $0.14 / 1M | tools, reasoning, open-weights |
| scx-ai/gpt-oss-120b | 131k | $0.17 / 1M | $0.55 / 1M | tools, reasoning, open-weights |
| together-ai/gpt-oss-120b | 131k | $0.15 / 1M | $0.60 / 1M | tools, reasoning, open-weights |
| together-ai/gpt-oss-20b | 131k | $0.05 / 1M | $0.20 / 1M | tools, reasoning, open-weights |
| mistral/codestral-2508 | 256k | $0.30 / 1M | $0.90 / 1M | — |
| nebius/qwen3-30b-a3b-instruct-2507 | 262k | $0.10 / 1M | $0.30 / 1M | tools |
| alibaba/qwen-flash | 1000k | $0.05 / 1M | $0.40 / 1M | tools |
| alibaba/qwen3-coder-flash | 1000k | $0.30 / 1M | $1.50 / 1M | tools |
| embercloud/glm-4.5 | 131k | $0.60 / 1M | $2.20 / 1M | tools, open-weights |
| embercloud/glm-4.5-air | 131k | $0.13 / 1M | $0.85 / 1M | tools, open-weights |
| zai/glm-4.5 | 128k | $0.60 / 1M | $2.20 / 1M | tools, reasoning, open-weights |
| zai/glm-4.5-air | 128k | $0.20 / 1M | $1.10 / 1M | tools, open-weights |
| zai/glm-4.5-airx | 128k | $1.10 / 1M | $4.50 / 1M | tools |
| zai/glm-4.5-x | 128k | $2.20 / 1M | $8.90 / 1M | tools, reasoning |
| bytedance/seed-1-6-flash-250715 | 256k | $0.07 / 1M | $0.30 / 1M | tools, reasoning, vision |
| novita/qwen3-235b-a22b-thinking-2507 | 131k | $0.30 / 1M | $3.00 / 1M | tools |
| alibaba/qwen3-coder-plus | 1000k | $6.00 / 1M | $60.00 / 1M | tools |
| cerebras/qwen3-235b-a22b-instruct-2507 | 262k | $0.60 / 1M | $1.20 / 1M | tools, open-weights |
| nebius/qwen3-235b-a22b-instruct-2507 | 262k | $0.20 / 1M | $0.60 / 1M | tools, open-weights |
| novita/qwen3-235b-a22b-instruct-2507 | 131k | $0.09 / 1M | $0.58 / 1M | tools, open-weights |
| vertex-openai/qwen3-235b-a22b-instruct-2507 | 262k | $0.22 / 1M | $0.88 / 1M | tools, open-weights |
| novita/kimi-k2 | 131k | $0.57 / 1M | $2.30 / 1M | tools |
| xai/grok-4 | 256k | $3.00 / 1M | $15.00 / 1M | tools, reasoning, vision |
| novita/ernie-4.5-vl-424b-a47b | 123k | $0.42 / 1M | $1.25 / 1M | reasoning, vision |
| bytedance/seed-1-6-250615 | 256k | $0.25 / 1M | $2.00 / 1M | tools, reasoning, vision |
| mistral/mistral-small-2506 | 128k | $0.10 / 1M | $0.30 / 1M | open-weights, vision |
| google-ai-studio/gemini-2.5-flash | 1049k | $0.30 / 1M | $2.50 / 1M | tools, reasoning, vision |
| google-ai-studio/gemini-2.5-flash-lite | 1049k | $0.10 / 1M | $0.40 / 1M | tools, vision |
| google-ai-studio/gemini-2.5-pro | 1049k | $1.25 / 1M | $10.00 / 1M | tools, reasoning, vision |
| google-vertex/gemini-2.5-flash | 1049k | $0.30 / 1M | $2.50 / 1M | tools, reasoning, vision |
| google-vertex/gemini-2.5-flash-lite | 1049k | $0.10 / 1M | $0.40 / 1M | tools, vision |
| google-vertex/gemini-2.5-pro | 1049k | $1.25 / 1M | $10.00 / 1M | tools, reasoning, vision |
| novita/qwen3-235b-a22b-fp8 | 41k | $0.20 / 1M | $0.80 / 1M | — |
| azure/o3 | 200k | $2.00 / 1M | $8.00 / 1M | vision |
| azure/o4-mini | 200k | $1.10 / 1M | $4.40 / 1M | tools, reasoning, vision |
| openai/o3 | 200k | $2.00 / 1M | $8.00 / 1M | vision |
| openai/o4-mini | 200k | $1.10 / 1M | $4.40 / 1M | tools, reasoning, vision |
| azure/gpt-4.1 | 1000k | $2.00 / 1M | $8.00 / 1M | tools, vision |
| azure/gpt-4.1-mini | 1000k | $0.40 / 1M | $1.60 / 1M | tools, vision |
| azure/gpt-4.1-nano | 1000k | $0.10 / 1M | $0.40 / 1M | tools, vision |
| openai/gpt-4.1 | 1000k | $2.00 / 1M | $8.00 / 1M | tools, vision |
| openai/gpt-4.1-mini | 1000k | $0.40 / 1M | $1.60 / 1M | tools, vision |
| openai/gpt-4.1-nano | 1000k | $0.10 / 1M | $0.40 / 1M | tools, vision |
| zai/glm-4-32b-0414-128k | 128k | $0.10 / 1M | $0.10 / 1M | tools |
| nebius/llama-3.1-nemotron-ultra-253b | 128k | $0.60 / 1M | $1.80 / 1M | — |
| aws-bedrock/llama-4-maverick-17b-instruct | 8k | $0.24 / 1M | $0.97 / 1M | open-weights, vision |
| aws-bedrock/llama-4-scout-17b-instruct | 8k | $0.17 / 1M | $0.66 / 1M | open-weights, vision |
| novita/llama-4-maverick-17b-instruct | 1049k | $0.27 / 1M | $0.85 / 1M | open-weights, vision |
| novita/llama-4-scout-17b-instruct | 131k | $0.18 / 1M | $0.59 / 1M | open-weights, vision |
| scx-ai/llama-4-maverick-17b-instruct | 131k | $0.53 / 1M | $1.62 / 1M | tools, open-weights |
| nebius/qwen3-32b | 41k | $0.10 / 1M | $0.30 / 1M | tools, open-weights |
| novita/qwen3-coder-30b-a3b-instruct | 160k | $0.07 / 1M | $0.27 / 1M | tools, open-weights |
| novita/qwen3-coder-480b-a35b-instruct | 262k | $0.38 / 1M | $1.55 / 1M | tools, open-weights |
| scx-ai/qwen3-32b | 33k | $0.36 / 1M | $0.87 / 1M | tools, reasoning, open-weights |
| vertex-openai/qwen3-coder-480b-a35b-instruct | 262k | $0.22 / 1M | $1.80 / 1M | tools, open-weights |
| openai/gpt-4o-mini-transcribe | 16k | $1.25 / 1M | $5.00 / 1M | — |
| openai/gpt-4o-transcribe | 16k | $2.50 / 1M | $10.00 / 1M | — |
| nebius/gemma-3-27b | 110k | $0.10 / 1M | $0.30 / 1M | vision |
| alibaba/qwen-omni-turbo | 33k | $0.20 / 1M | $0.80 / 1M | vision |
| minimax/minimax-text-01 | 1000k | $0.20 / 1M | $1.10 / 1M | tools, reasoning |
| azure/o3-mini | 200k | $1.10 / 1M | $4.40 / 1M | — |
| openai/o3-mini | 200k | $1.10 / 1M | $4.40 / 1M | — |
| cerebras/llama-3.3-70b-instruct | 128k | $0.85 / 1M | $1.20 / 1M | tools, open-weights |
| nebius/llama-3.3-70b-instruct | 128k | $0.13 / 1M | $0.40 / 1M | tools, open-weights |
| novita/llama-3.3-70b-instruct | 131k | $0.14 / 1M | $0.40 / 1M | tools, open-weights |
| azure/o1 | 200k | $15.00 / 1M | $60.00 / 1M | reasoning, vision |
| openai/o1 | 200k | $15.00 / 1M | $60.00 / 1M | reasoning, vision |
| mistral/mistral-large-2512 | 262k | $0.50 / 1M | $1.50 / 1M | open-weights, vision |
| mistral/mistral-large-latest | 128k | $4.00 / 1M | $12.00 / 1M | open-weights |
| inference.net/llama-3.2-11b-instruct | 128k | $0.07 / 1M | $0.33 / 1M | — |
| alibaba/qwen-coder-plus | 131k | $0.50 / 1M | $1.00 / 1M | tools |
| novita/llama-3.2-3b-instruct | 33k | $0.03 / 1M | $0.05 / 1M | — |
| alibaba/qwen-plus-latest | 1000k | $0.40 / 1M | $1.20 / 1M | tools |
| nebius/qwen2-5-vl-72b-instruct | 32k | $0.25 / 1M | $0.75 / 1M | open-weights, vision |
| aws-bedrock/llama-3.1-70b-instruct | 128k | $0.72 / 1M | $0.72 / 1M | — |
| openai/gpt-4o-mini | 128k | $0.15 / 1M | $0.60 / 1M | tools, vision |
| azure/gpt-4o | 128k | $2.50 / 1M | $10.00 / 1M | tools, vision |
| openai/gpt-4o | 128k | $2.50 / 1M | $10.00 / 1M | tools, vision |
| novita/llama-3-70b-instruct | 8k | $0.51 / 1M | $0.74 / 1M | — |
| alibaba/qwen-max | 33k | $1.60 / 1M | $6.40 / 1M | tools |
| alibaba/qwen-plus | 131k | $0.40 / 1M | $1.20 / 1M | tools |
| perplexity/sonar | 130k | $1.00 / 1M | $1.00 / 1M | — |
| perplexity/sonar-pro | 200k | $3.00 / 1M | $15.00 / 1M | — |
| perplexity/sonar-reasoning-pro | 128k | $2.00 / 1M | $8.00 / 1M | — |
| azure/gpt-4 | 8k | $30.00 / 1M | $60.00 / 1M | tools |
| azure/gpt-4-turbo | 128k | $10.00 / 1M | $30.00 / 1M | tools, vision |
| openai/gpt-4 | 8k | $30.00 / 1M | $60.00 / 1M | tools |
| openai/gpt-4-turbo | 128k | $10.00 / 1M | $30.00 / 1M | tools, vision |
| azure/gpt-3.5-turbo | 16k | $0.50 / 1M | $1.50 / 1M | tools |
| openai/gpt-3.5-turbo | 16k | $0.50 / 1M | $1.50 / 1M | tools |
Sourced from models.dev. Pricing reflects the catalog at the time this page was rendered.