LLM Gateway
- 431
- Models
- 21
- Labs
Models on this provider
USD per 1M tokens
| Model | Provider model ID | Context | Output | Input $ | Output $ | Cache read | Cache write | Reasoning | Tools | Structured | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|
| openai/gpt-6.1-terra | 1.05M | 128K | $1.00 | $5.00 | $0.05 | $1.25 | Yes | Yes | Yes | Oct 26, 2026 | |
| moonshot/kimi-k3.1-pro | 1.05M | 1.05M | $2.00 | $10.00 | $0.20 | $2.00 | Yes | Yes | Yes | Oct 23, 2026 | |
| moonshot/kimi-k3.1-pro-highspeed | 1.05M | 1.05M | $4.00 | $20.00 | $0.20 | $4.00 | Yes | Yes | Yes | Oct 23, 2026 | |
| minimax/minimax-m3.1-flash | 1.05M | 524K | $0.15 | $0.60 | $0.01 | — | Yes | Yes | No | Oct 19, 2026 | |
| together-ai/minimax-m3.1-flash | 1.05M | 1.05M | $0.15 | $0.60 | $0.01 | — | Yes | Yes | No | Oct 19, 2026 | |
| inference.net/minimax-m3.1-flash | 1M | 524K | $0.10 | $0.50 | $0.005 | — | Yes | Yes | No | Oct 19, 2026 | |
| nebius/minimax-m3.1-flash | 1.05M | 1.05M | $0.15 | $0.60 | $0.01 | — | Yes | Yes | No | Oct 19, 2026 | |
| novita/minimax-m3.1-flash | 1M | 524K | $0.15 | $0.60 | $0.01 | — | Yes | Yes | No | Oct 19, 2026 | |
| deepseek/deepseek-v4.1-flash-1017 | 1.05M | 393K | $0.15 | $0.60 | $0.003 | — | Yes | Yes | No | Oct 17, 2026 | |
| alibaba/deepseek-v4.1-flash-1017 | 1M | 393K | $0.30 | $1.20 | $0.03 | — | Yes | Yes | No | Oct 17, 2026 | |
| reka-ai/deepseek-v4.1-flash-1017 | 1.05M | 393K | $0.15 | $0.60 | $0.003 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| together-ai/deepseek-v4.1-flash-1017 | 1.05M | 393K | $0.30 | $1.20 | $0.006 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| sciforium/deepseek-v4.1-flash-1017 | 1.06M | 384K | $0.15 | $0.60 | $0.003 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| runware/deepseek-v4.1-flash-1017 | 1.05M | 1.05M | $0.15 | $0.60 | $0.01 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| inference.net/deepseek-v4.1-flash-1017 | 262K | 131K | $0.30 | $1.00 | $0.007 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| entrim/deepseek-v4.1-flash-1017 | 1.05M | 384K | $0.20 | $0.80 | $0.005 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| deepinfra/deepseek-v4.1-flash-1017 | 1.05M | 393K | $0.20 | $0.60 | $0.006 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| novita/deepseek-v4.1-flash-1017 | 1.05M | 393K | $0.30 | $1.20 | $0.006 | — | Yes | Yes | No | Oct 17, 2026 | |
| google-vertex/gemini-4-argon | 1.05M | 1.05M | $4.00 | $20.00 | $0.20 | $0.38 | Yes | Yes | Yes | Oct 13, 2026 | |
| google-ai-studio/gemini-4-argon | 1.05M | 1.05M | $4.00 | $20.00 | $0.20 | $0.38 | Yes | Yes | Yes | Oct 13, 2026 | |
| meta/muse-wonder-1.0 | 1.05M | 1.05M | $4.00 | $20.00 | $0.20 | — | Yes | Yes | Yes | Oct 12, 2026 | |
| anthropic/claude-haiku-5-5 | 1M | 128K | $0.10 | $0.50 | $0.01 | $0.13 | Yes | Yes | Yes | Oct 7, 2026 | |
| aws-bedrock/claude-haiku-5-5 | 1M | 128K | $0.10 | $0.50 | $0.01 | $0.13 | Yes | Yes | No | Oct 7, 2026 | |
| mistral/mistral-large-4 | 1M | 262K | $1.36 | $4.18 | $0.14 | — | No | Yes | Yes | Oct 6, 2026 | |
| openai/gpt-6.1-sol | 1.05M | 128K | $2.00 | $10.00 | $0.10 | $2.50 | Yes | Yes | Yes | Sep 29, 2026 | |
| azure/gpt-6.1-sol | 1.05M | 128K | $2.00 | $10.00 | $0.10 | $2.50 | Yes | Yes | Yes | Sep 29, 2026 | |
| anthropic/claude-sonnet-5-5 | 1M | 128K | $2.00 | $10.00 | $0.10 | $2.50 | Yes | Yes | Yes | Sep 28, 2026 | |
| azure-anthropic/claude-sonnet-5-5 | 1M | 128K | $2.00 | $10.00 | $0.10 | $2.50 | Yes | Yes | Yes | Sep 28, 2026 | |
| aws-bedrock/claude-sonnet-5-5 | 1M | 128K | $2.00 | $10.00 | $0.10 | $2.50 | Yes | Yes | No | Sep 28, 2026 | |
| anthropic/claude-opus-5-5 | 1M | 128K | $4.00 | $20.00 | $0.20 | $5.00 | Yes | Yes | Yes | Sep 22, 2026 | |
| azure-anthropic/claude-opus-5-5 | 1M | 128K | $4.00 | $20.00 | $0.20 | $5.00 | Yes | Yes | Yes | Sep 22, 2026 | |
| aws-bedrock/claude-opus-5-5 | 1M | 128K | $4.00 | $20.00 | $0.20 | $5.00 | Yes | Yes | No | Sep 22, 2026 | |
| openai/gpt-6-luna | 1.05M | 128K | $0.10 | $0.50 | $0.01 | $0.13 | Yes | Yes | Yes | Sep 22, 2026 | |
| azure/gpt-6-luna | 1.05M | 128K | $0.10 | $0.50 | $0.01 | $0.13 | Yes | Yes | Yes | Sep 22, 2026 | |
| openai/gpt-6-sol | 1.05M | 128K | $2.00 | $10.00 | $0.20 | $2.50 | Yes | Yes | Yes | Sep 22, 2026 | |
| azure/gpt-6-sol | 1.05M | 128K | $2.00 | $10.00 | $0.20 | $2.50 | Yes | Yes | Yes | Sep 22, 2026 | |
| xiaomi/mimo-v2.6-flash | 1M | 131K | $0.14 | $0.28 | $0.0028 | — | Yes | Yes | No | Sep 22, 2026 | |
| deepinfra/mimo-v2.6-flash | 1.05M | 66K | $0.14 | $0.28 | $0.0028 | — | Yes | Yes | Yes | Sep 22, 2026 | |
| consensusprotocol/mimo-v2.6-flash | 1.05M | 131K | $0.12 | $0.25 | $0.0025 | — | Yes | Yes | Yes | Sep 22, 2026 | |
| xiaomi/mimo-v2.6-pro | 1M | 131K | $0.43 | $0.87 | $0.0036 | — | Yes | Yes | No | Sep 22, 2026 | |
| deepinfra/mimo-v2.6-pro | 1.05M | 66K | $0.43 | $0.87 | $0.0036 | — | Yes | Yes | Yes | Sep 22, 2026 | |
| xai/grok-4-7 | 500K | 500K | $2.00 | $6.00 | $0.50 | — | Yes | Yes | No | Sep 21, 2026 | |
| vertex-openai/grok-4-7 | 524K | 524K | $2.00 | $6.00 | $0.50 | — | Yes | Yes | Yes | Sep 21, 2026 | |
| aws-bedrock/grok-4-7 | 524K | 524K | $2.00 | $6.00 | $0.50 | — | Yes | Yes | Yes | Sep 21, 2026 | |
| sakana/fugu-max | 1M | 1M | $2.00 | $6.00 | $0.25 | — | Yes | Yes | Yes | Sep 11, 2026 | |
| sakana/fugu-ultra-v2.0 | 1M | 1M | $5.00 | $30.00 | $0.50 | — | Yes | Yes | Yes | Sep 11, 2026 | |
| scx-ai-gp/deepseek-v4.1-flash | 1M | 384K | $0.15 | $0.60 | $0.01 | — | No | No | No | Sep 10, 2026 | |
| luminal/deepseek-v4.1-flash | 1M | 384K | $0.14 | $0.54 | $0.0027 | — | Yes | Yes | No | Sep 10, 2026 | |
| baidu/deepseek-v4.1-flash | 1.05M | 393K | $0.30 | $1.20 | $0.006 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| alibaba/deepseek-v4.1-flash | 1M | 393K | $0.30 | $1.20 | $0.03 | — | Yes | Yes | No | Sep 10, 2026 | |
| reka-ai/deepseek-v4.1-flash | 1.05M | 393K | $0.10 | $0.30 | $0.0025 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| together-ai/deepseek-v4.1-flash | 1.05M | 393K | $0.30 | $1.20 | $0.006 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| runware/deepseek-v4.1-flash | 1.05M | 384K | $0.15 | $0.60 | $0.01 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| entrim/deepseek-v4.1-flash | 1.05M | 384K | $0.20 | $0.60 | $0.005 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| deepinfra/deepseek-v4.1-flash | 1.05M | 393K | $0.20 | $0.60 | $0.006 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| fireworks/deepseek-v4.1-flash | 1.05M | 393K | $0.22 | $0.66 | $0.007 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| consensusprotocol/deepseek-v4.1-flash | 1.05M | 384K | $0.15 | $0.55 | $0.005 | — | Yes | Yes | No | Sep 10, 2026 | |
| novita/deepseek-v4.1-flash | 1.05M | 393K | $0.30 | $1.20 | $0.006 | — | Yes | Yes | No | Sep 10, 2026 | |
| deepinfra/ling-3.0-flash-vl | 131K | 33K | $0.06 | $0.18 | $0.01 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| aws-mantle/gpt-6-astra | 1.05M | 128K | $10.00 | $50.00 | $1.00 | $12.50 | Yes | Yes | Yes | Sep 4, 2026 | |
| openai/gpt-6-astra | 1.05M | 128K | $10.00 | $50.00 | $1.00 | $12.50 | Yes | Yes | Yes | Sep 4, 2026 | |
| azure/gpt-6-astra | 1.05M | 128K | $10.00 | $50.00 | $1.00 | $12.50 | Yes | Yes | Yes | Sep 4, 2026 | |
| google-vertex/gemini-3.8-flash | 1.05M | 66K | $0.75 | $3.75 | $0.07 | $0.08 | Yes | Yes | Yes | Sep 2, 2026 | |
| google-ai-studio/gemini-3.8-flash | 1.05M | 66K | $0.75 | $3.75 | $0.07 | $0.08 | Yes | Yes | Yes | Sep 2, 2026 | |
| meta/muse-spark-1.3 | 1.05M | 1.05M | $1.25 | $4.25 | $0.15 | — | Yes | Yes | Yes | Sep 2, 2026 | |
| meta-contributor/muse-spark-1.3-contributor | 1.05M | 1.05M | $0.10 | $0.20 | $0.002 | — | Yes | Yes | Yes | Sep 2, 2026 | |
| anthropic/claude-fable-5-1 | 1M | 128K | $10.00 | $50.00 | $0.25 | $12.50 | Yes | Yes | Yes | Sep 1, 2026 | |
| azure-anthropic/claude-fable-5-1 | 1M | 128K | $10.00 | $50.00 | $0.25 | $12.50 | Yes | Yes | Yes | Sep 1, 2026 | |
| aws-bedrock/claude-fable-5-1 | 1M | 128K | $10.00 | $50.00 | $0.25 | $12.50 | Yes | Yes | No | Sep 1, 2026 | |
| tencent/hy4-preview | 1M | 66K | $0.83 | $2.50 | $0.04 | — | Yes | Yes | Yes | Aug 28, 2026 | |
| scx-ai-gp/glm-5.3-flash | 1.05M | 131K | $0.09 | $0.25 | $0.03 | — | Yes | Yes | No | Aug 26, 2026 | |
| greenference/glm-5.3-flash | 1.05M | 131K | $0.14 | $0.49 | $0.03 | — | Yes | Yes | No | Aug 26, 2026 | |
| reka-ai/glm-5.3-flash | 262K | 262K | $0.15 | $0.50 | $0.02 | — | Yes | Yes | Yes | Aug 26, 2026 | |
| together-ai/glm-5.3-flash | 1.05M | 944K | $0.15 | $0.50 | $0.03 | — | Yes | Yes | Yes | Aug 26, 2026 | |
| runware/glm-5.3-flash | 1M | 131K | $0.15 | $0.50 | $0.03 | — | Yes | Yes | Yes | Aug 26, 2026 | |
| inference.net/glm-5.3-flash | 1.05M | 128K | $0.09 | $0.28 | $0.02 | — | Yes | Yes | Yes | Aug 26, 2026 | |
| zai/glm-5.3-flash | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | Yes | Yes | No | Aug 26, 2026 | |
| entrim/glm-5.3-flash | 1.05M | 131K | $0.10 | $0.35 | $0.02 | — | Yes | Yes | Yes | Aug 26, 2026 | |
| fireworks/glm-5.3-flash | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | Yes | Yes | No | Aug 26, 2026 | |
| consensusprotocol/glm-5.3-flash | 1.05M | 131K | $0.10 | $0.25 | $0.01 | — | Yes | Yes | No | Aug 26, 2026 | |
| novita/glm-5.3-flash | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | Yes | Yes | No | Aug 26, 2026 | |
| alibaba/qwen3.8-flash | 984K | 131K | $0.15 | $0.47 | $0.02 | $0.20 | Yes | Yes | Yes | Aug 26, 2026 | |
| novita/qwen3.8-flash | 1M | 131K | $0.15 | $0.47 | $0.02 | — | Yes | Yes | Yes | Aug 26, 2026 | |
| deepinfra/granite-4.2-8b | 131K | 118K | $0.06 | $0.25 | $0.01 | — | Yes | Yes | No | Aug 25, 2026 | |
| scx-ai-gp/glm-5.3-fast | 1M | 128K | $2.80 | $8.80 | $0.56 | — | No | No | No | Aug 14, 2026 | |
| scx-ai-gp/glm-5.3 | 1M | 128K | $0.92 | $2.90 | $0.17 | — | Yes | Yes | No | Aug 14, 2026 | |
| baidu/glm-5.3 | 1.05M | 131K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Aug 14, 2026 | |
| alibaba/glm-5.3 | 1.05M | 131K | $1.40 | $4.40 | $0.28 | — | Yes | Yes | No | Aug 14, 2026 | |
| reka-ai/glm-5.3 | 1.05M | 262K | $0.45 | $1.80 | $0.14 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| together-ai/glm-5.3 | 1.05M | 944K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| runware/glm-5.3 | 1M | 131K | $1.20 | $4.00 | $0.20 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| inference.net/glm-5.3 | 1.05M | 131K | $0.90 | $3.00 | $0.15 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| zai/glm-5.3 | 1M | 128K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Aug 14, 2026 | |
| entrim/glm-5.3 | 1.05M | 131K | $0.50 | $2.00 | $0.15 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| mistral/glm-5.3 | 1.05M | 131K | $1.40 | $4.40 | $0.14 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| fireworks/glm-5.3 | 1.05M | 131K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Aug 14, 2026 | |
| novita/glm-5.3 | 1.05M | 131K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Aug 14, 2026 | |
| consensusprotocol/Qwen3.8-27B | 262K | 33K | $0.08 | $0.35 | $0.05 | — | Yes | Yes | No | Aug 14, 2026 | |
| novita/qwen3.8-27b | 1M | 131K | $0.42 | $3.00 | $0.09 | — | Yes | Yes | No | Aug 14, 2026 | |
| google-vertex/gemini-3.7-flash | 1.05M | 66K | $0.75 | $3.75 | $0.07 | $0.08 | Yes | Yes | Yes | Aug 13, 2026 | |
| xai/grok-4-6 | 500K | 500K | $2.00 | $6.00 | $0.50 | — | Yes | Yes | No | Aug 12, 2026 | |
| vertex-openai/grok-4-6 | 500K | 500K | $2.00 | $6.00 | $0.50 | — | Yes | Yes | Yes | Aug 12, 2026 | |
| aws-bedrock/grok-4-6 | 500K | 500K | $2.00 | $6.00 | $0.50 | — | Yes | Yes | Yes | Aug 12, 2026 | |
| together-ai/qwen3.8-2.4t-a95b | 1.01M | 909K | $2.00 | $6.00 | $0.25 | — | Yes | Yes | Yes | Aug 12, 2026 | |
| novita/qwen3.8-2.4t-a95b | 1M | 131K | $2.00 | $6.00 | $0.25 | — | Yes | Yes | Yes | Aug 12, 2026 | |
| together-ai/muse-glimmer-30b | 131K | 118K | $0.35 | $1.50 | $0.04 | — | Yes | Yes | Yes | Aug 10, 2026 | |
| deepinfra/muse-glimmer-30b | 131K | 16K | $0.30 | $1.20 | $0.04 | — | Yes | Yes | Yes | Aug 10, 2026 | |
| meta-contributor/muse-spark-1.2-contributor | 1.05M | 131K | $0.10 | $0.20 | $0.002 | — | Yes | Yes | Yes | Aug 6, 2026 | |
| meta/muse-spark-1.2 | 1.05M | 131K | $1.25 | $4.25 | $0.15 | — | Yes | Yes | Yes | Aug 5, 2026 | |
| scx-ai-gp/qwen3.8-max | 1M | 131K | $1.54 | $4.63 | $0.20 | $2.50 | Yes | Yes | No | Aug 3, 2026 | |
| alibaba/qwen3.8-max | 984K | 131K | $2.00 | $6.00 | $0.25 | $2.50 | Yes | Yes | No | Aug 3, 2026 | |
| novita/qwen3.8-max | 1M | 131K | $2.00 | $6.00 | $0.25 | — | Yes | Yes | Yes | Aug 3, 2026 | |
| openai/gpt-live-transcribe | — | — | Free | Free | — | — | No | No | No | Jul 28, 2026 | |
| openai/gpt-transcribe | — | — | Free | Free | — | — | No | No | No | Jul 28, 2026 | |
| anthropic/claude-opus-5 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Jul 24, 2026 | |
| azure-anthropic/claude-opus-5 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Jul 24, 2026 | |
| aws-bedrock/claude-opus-5 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | No | Jul 24, 2026 | |
| deepinfra/ling-3.0-flash | 262K | 33K | $0.06 | $0.18 | $0.01 | — | Yes | Yes | No | Jul 23, 2026 | |
| novita/ling-3.0-flash | 262K | 33K | $0.06 | $0.18 | $0.01 | — | Yes | Yes | No | Jul 23, 2026 | |
| google-vertex/gemini-3.5-flash-lite | 1.05M | 66K | $0.30 | $2.50 | $0.03 | $0.08 | Yes | Yes | Yes | Jul 21, 2026 | |
| google-ai-studio/gemini-3.5-flash-lite | 1.05M | 66K | $0.30 | $2.50 | $0.03 | $0.08 | Yes | Yes | Yes | Jul 21, 2026 | |
| google-vertex/gemini-3.6-flash | 1.05M | 66K | $0.75 | $3.75 | $0.07 | $0.08 | Yes | Yes | Yes | Jul 21, 2026 | |
| google-ai-studio/gemini-3.6-flash | 1.05M | 66K | $0.75 | $3.75 | $0.07 | $0.08 | Yes | Yes | Yes | Jul 21, 2026 | |
| scx-ai-gp/kimi-k3 | 1.05M | 1.05M | $3.13 | $15.68 | $0.32 | — | Yes | Yes | Yes | Jul 16, 2026 | |
| alibaba/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | Yes | Jul 16, 2026 | |
| canopywave/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | No | Jul 16, 2026 | |
| moonshot/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | No | Jul 16, 2026 | |
| together-ai/kimi-k3 | 1M | 1M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | No | Jul 16, 2026 | |
| tencent/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | Yes | Jul 16, 2026 | |
| runware/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | Yes | Jul 16, 2026 | |
| runpod/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | Yes | Jul 16, 2026 | |
| aws-bedrock/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Jul 16, 2026 | |
| fireworks/kimi-k3 | 1.04M | 1.04M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | No | Jul 16, 2026 | |
| fireworks/kimi-k3-fast | 1.04M | 1.04M | $4.50 | $22.50 | $0.45 | — | Yes | Yes | No | Jul 16, 2026 | |
| novita/kimi-k3 | 1.05M | 1.05M | $3.00 | $15.00 | $0.30 | — | Yes | Yes | No | Jul 16, 2026 | |
| alibaba/qwen3.7-flash | 984K | 66K | $0.03 | $0.13 | $0.006 | $0.04 | Yes | Yes | No | Jul 15, 2026 | |
| aws-mantle/gpt-5.6-luna | 922K | 128K | $0.22 | $1.32 | $0.02 | $0.28 | Yes | Yes | Yes | Jul 9, 2026 | |
| openai/gpt-5.6-luna | 1.05M | 128K | $0.20 | $1.20 | $0.02 | $0.25 | Yes | Yes | Yes | Jul 9, 2026 | |
| azure/gpt-5.6-luna | 1.05M | 128K | $0.20 | $1.20 | $0.02 | $0.25 | Yes | Yes | Yes | Jul 9, 2026 | |
| aws-mantle/gpt-5.6-sol | 922K | 128K | $4.40 | $22.00 | $0.44 | $5.50 | Yes | Yes | Yes | Jul 9, 2026 | |
| openai/gpt-5.6-sol | 1.05M | 128K | $4.00 | $20.00 | $0.40 | $5.00 | Yes | Yes | Yes | Jul 9, 2026 | |
| azure/gpt-5.6-sol | 1.05M | 128K | $4.00 | $20.00 | $0.40 | $5.00 | Yes | Yes | Yes | Jul 9, 2026 | |
| aws-mantle/gpt-5.6-terra | 922K | 128K | $2.20 | $13.20 | $0.22 | $2.75 | Yes | Yes | Yes | Jul 9, 2026 | |
| openai/gpt-5.6-terra | 1.05M | 128K | $2.00 | $12.00 | $0.20 | $2.50 | Yes | Yes | Yes | Jul 9, 2026 | |
| azure/gpt-5.6-terra | 1.05M | 128K | $2.00 | $12.00 | $0.20 | $2.50 | Yes | Yes | Yes | Jul 9, 2026 | |
| meta/muse-spark-1.1 | 1.05M | 131K | $1.25 | $4.25 | $0.15 | — | Yes | Yes | Yes | Jul 9, 2026 | |
| xai/grok-4-5 | 500K | 500K | $2.00 | $6.00 | $0.30 | — | Yes | Yes | No | Jul 8, 2026 | |
| tencent/hy3 | 262K | 131K | $0.13 | $0.53 | $0.03 | — | Yes | Yes | Yes | Jul 6, 2026 | |
| novita/hy3 | 262K | 262K | $0.14 | $0.58 | $0.04 | — | Yes | Yes | Yes | Jul 6, 2026 | |
| anthropic/claude-sonnet-5 | 1M | 128K | $2.00 | $10.00 | $0.20 | $2.50 | Yes | Yes | Yes | Jun 30, 2026 | |
| azure-anthropic/claude-sonnet-5 | 1M | 128K | $2.00 | $10.00 | $0.20 | $2.50 | Yes | Yes | Yes | Jun 30, 2026 | |
| aws-bedrock/claude-sonnet-5 | 1M | 128K | $2.00 | $10.00 | $0.20 | $2.50 | Yes | Yes | No | Jun 30, 2026 | |
| vertex-anthropic/claude-sonnet-5 | 1M | 128K | $2.00 | $10.00 | $0.20 | $2.50 | Yes | Yes | Yes | Jun 30, 2026 | |
| sakana/fugu-ultra | 1M | 1M | $5.00 | $30.00 | $0.50 | — | Yes | Yes | No | Jun 15, 2026 | |
| bytedance/glm-5.2 | 1.02M | 128K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Jun 13, 2026 | |
| scx-ai-gp/glm-5.2-fast | 1M | 131K | $2.16 | $6.78 | $0.43 | — | Yes | Yes | No | Jun 13, 2026 | |
| scx-ai-gp/glm-5.2 | 1M | 131K | $0.60 | $2.12 | $0.15 | — | Yes | Yes | No | Jun 13, 2026 | |
| baidu/glm-5.2 | 1.05M | 131K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Jun 13, 2026 | |
| alibaba/glm-5.2 | 1M | 131K | $1.40 | $4.40 | $0.28 | — | Yes | Yes | No | Jun 13, 2026 | |
| canopywave/glm-5.2 | 200K | 33K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Jun 13, 2026 | |
| tencent/glm-5.2 | 1M | 128K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Jun 13, 2026 | |
| runware/glm-5.2 | 1.02M | 128K | $0.80 | $2.55 | $0.16 | — | Yes | Yes | No | Jun 13, 2026 | |
| zai/glm-5.2 | 1M | 128K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Jun 13, 2026 | |
| embercloud/glm-5.2 | 203K | 131K | $1.26 | $3.96 | $0.23 | — | Yes | Yes | No | Jun 13, 2026 | |
| novita/glm-5.2 | 1.05M | 131K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Jun 13, 2026 | |
| scx-ai-gp/kimi-k2.7-code | 262K | 262K | $0.74 | $3.08 | $0.14 | — | Yes | Yes | No | Jun 12, 2026 | |
| moonshot/kimi-k2.7-code | 262K | 262K | $0.95 | $4.00 | $0.19 | — | Yes | Yes | No | Jun 12, 2026 | |
| tencent/kimi-k2.7-code | 262K | 262K | $0.95 | $4.00 | $0.19 | — | Yes | Yes | Yes | Jun 12, 2026 | |
| novita/kimi-k2.7-code | 262K | 262K | $0.95 | $4.00 | $0.19 | — | Yes | Yes | Yes | Jun 12, 2026 | |
| moonshot/kimi-k2.7-code-highspeed | 262K | 262K | $1.90 | $8.00 | $0.38 | — | Yes | Yes | No | Jun 12, 2026 | |
| tencent/kimi-k2.7-code-highspeed | 262K | 262K | $1.90 | $8.00 | $0.38 | — | Yes | Yes | Yes | Jun 12, 2026 | |
| anthropic/claude-fable-5 | 1M | 128K | $10.00 | $50.00 | $1.00 | $12.50 | Yes | Yes | Yes | Jun 9, 2026 | |
| azure-anthropic/claude-fable-5 | 1M | 128K | $10.00 | $50.00 | $1.00 | $12.50 | Yes | Yes | Yes | Jun 9, 2026 | |
| aws-bedrock/claude-fable-5 | 1M | 128K | $10.00 | $50.00 | $1.00 | $12.50 | Yes | Yes | No | Jun 9, 2026 | |
| alibaba/qwen3.7-plus | 984K | 66K | $0.40 | $1.60 | $0.08 | $0.50 | Yes | Yes | No | Jun 2, 2026 | |
| minimax/minimax-m3 | 512K | 131K | $0.60 | $2.40 | $0.12 | — | Yes | Yes | No | Jun 1, 2026 | |
| together-ai/minimax-m3 | 524K | 131K | $0.30 | $1.20 | $0.06 | — | Yes | No | Yes | Jun 1, 2026 | |
| tencent/minimax-m3 | 1M | 131K | $0.30 | $1.20 | $0.06 | — | Yes | Yes | No | Jun 1, 2026 | |
| consensusprotocol/minimax-m3 | 1.05M | 512K | $0.28 | $1.10 | $0.05 | — | Yes | Yes | Yes | Jun 1, 2026 | |
| deepinfra/nemotron-3-ultra-550b | 262K | 262K | $0.50 | $2.20 | $0.10 | — | No | Yes | No | Jun 1, 2026 | |
| novita/step-3.7-flash | 262K | 256K | $0.20 | $1.15 | $0.04 | — | Yes | Yes | No | May 29, 2026 | |
| anthropic/claude-opus-4-8 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | May 28, 2026 | |
| azure-anthropic/claude-opus-4-8 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | May 28, 2026 | |
| aws-bedrock/claude-opus-4-8 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | No | May 28, 2026 | |
| tencent/hy-mt2-plus | 8K | 4K | $0.07 | $0.29 | — | — | No | No | No | May 21, 2026 | |
| alibaba/qwen3.7-max | 984K | 66K | $2.50 | $7.50 | $0.50 | $3.13 | Yes | Yes | No | May 21, 2026 | |
| novita/qwen3.7-max | 1M | 66K | $1.25 | $3.75 | $0.25 | — | Yes | Yes | No | May 21, 2026 | |
| google-vertex/gemini-3.5-flash | 1.05M | 66K | $1.50 | $9.00 | $0.15 | $0.08 | Yes | Yes | Yes | May 19, 2026 | |
| google-vertex/gemini-3.1-flash-lite | 1.05M | 66K | $0.25 | $1.50 | $0.03 | $0.08 | Yes | Yes | Yes | May 7, 2026 | |
| google-ai-studio/gemini-3.1-flash-lite | 1.05M | 66K | $0.25 | $1.50 | $0.03 | $0.08 | Yes | Yes | Yes | May 7, 2026 | |
| mistral/mistral-medium-3-5 | 262K | 262K | $1.50 | $7.50 | — | — | No | Yes | Yes | Apr 30, 2026 | |
| bytedance/seed-2-0-lite-260428 | 262K | 131K | $0.25 | $2.00 | $0.05 | — | Yes | Yes | Yes | Apr 28, 2026 | |
| bytedance/seed-2-0-mini-260428 | 262K | 131K | $0.10 | $0.40 | $0.02 | — | Yes | Yes | Yes | Apr 28, 2026 | |
| alibaba/qwen3.6-flash | 984K | 66K | $0.25 | $1.50 | $0.05 | $0.31 | Yes | Yes | No | Apr 27, 2026 | |
| bytedance/deepseek-v4-flash | 1.05M | 393K | $0.44 | $1.32 | $0.01 | — | Yes | Yes | No | Apr 24, 2026 | |
| ranoai/deepseek-v4-flash | 1M | 393K | $0.14 | $0.28 | $0.03 | — | Yes | Yes | Yes | Apr 24, 2026 | |
| baidu/deepseek-v4-flash | 1.05M | 131K | $0.44 | $1.32 | $0.01 | — | Yes | Yes | No | Apr 24, 2026 | |
| alibaba/deepseek-v4-flash | 1M | 393K | $0.20 | $0.40 | $0.04 | — | Yes | Yes | No | Apr 24, 2026 | |
| canopywave/deepseek-v4-flash | 1M | 393K | $0.14 | $0.28 | $0.03 | — | Yes | Yes | No | Apr 24, 2026 | |
| tencent/deepseek-v4-flash | 1M | 393K | $0.14 | $0.28 | $0.0028 | — | Yes | Yes | No | Apr 24, 2026 | |
| runware/deepseek-v4-flash | 1.05M | 384K | $0.08 | $0.15 | $0.01 | — | Yes | Yes | Yes | Apr 24, 2026 | |
| deepinfra/deepseek-v4-flash | 1M | 393K | $0.08 | $0.18 | $0.02 | — | Yes | Yes | No | Apr 24, 2026 | |
| consensusprotocol/deepseek-v4-flash | 1M | 384K | $0.10 | $0.20 | $0.005 | — | Yes | Yes | No | Apr 24, 2026 | |
| novita/deepseek-v4-flash | 1.05M | 393K | $0.14 | $0.28 | $0.03 | — | Yes | Yes | No | Apr 24, 2026 | |
| bytedance/deepseek-v4-pro | 1.05M | 393K | $1.32 | $3.96 | $0.04 | — | Yes | Yes | No | Apr 24, 2026 | |
| deepseek/deepseek-v4-pro | 1.05M | 393K | $0.43 | $0.87 | $0.0036 | — | Yes | Yes | No | Apr 24, 2026 | |
| baidu/deepseek-v4-pro | 1.05M | 131K | $1.32 | $3.96 | $0.04 | — | Yes | Yes | No | Apr 24, 2026 | |
| alibaba/deepseek-v4-pro | 1M | 393K | $2.40 | $4.80 | $0.20 | — | Yes | Yes | No | Apr 24, 2026 | |
| reka-ai/deepseek-v4-pro | 1.05M | 393K | $0.90 | $1.90 | $0.07 | — | Yes | Yes | Yes | Apr 24, 2026 | |
| canopywave/deepseek-v4-pro | 1M | 393K | $1.74 | $3.48 | $0.01 | — | Yes | Yes | No | Apr 24, 2026 | |
| together-ai/deepseek-v4-pro | 1.05M | 164K | $1.32 | $3.96 | $0.13 | — | Yes | Yes | Yes | Apr 24, 2026 | |
| tencent/deepseek-v4-pro | 1M | 393K | $0.43 | $0.87 | $0.0036 | — | Yes | Yes | No | Apr 24, 2026 | |
| runware/deepseek-v4-pro | 1.05M | 384K | $0.96 | $1.92 | $0.08 | — | Yes | Yes | Yes | Apr 24, 2026 | |
| deepinfra/deepseek-v4-pro | 1.05M | 64K | $1.30 | $2.60 | $0.10 | — | Yes | Yes | No | Apr 24, 2026 | |
| openai/gpt-5.5 | 1.05M | 128K | $5.00 | $30.00 | $0.50 | — | Yes | Yes | Yes | Apr 23, 2026 | |
| azure/gpt-5.5 | 1.05M | 128K | $5.00 | $30.00 | $0.50 | — | Yes | Yes | Yes | Apr 23, 2026 | |
| openai/gpt-5.5-pro | 1.05M | 128K | $30.00 | $180 | — | — | Yes | Yes | No | Apr 23, 2026 | |
| greenference/qwen3.6-27b | 16K | 8K | $0.15 | $1.35 | — | — | No | Yes | Yes | Apr 22, 2026 | |
| baidu/kimi-k2.6 | 262K | 262K | $0.95 | $4.00 | $0.16 | — | Yes | Yes | No | Apr 20, 2026 | |
| canopywave/kimi-k2.6 | 262K | 33K | $0.95 | $4.00 | $0.16 | — | Yes | Yes | No | Apr 20, 2026 | |
| moonshot/kimi-k2.6 | 262K | 262K | $0.95 | $4.00 | $0.16 | — | Yes | Yes | No | Apr 20, 2026 | |
| tencent/kimi-k2.6 | 262K | 262K | $0.86 | $3.57 | $0.14 | — | Yes | Yes | Yes | Apr 20, 2026 | |
| runware/kimi-k2.6 | 262K | 131K | $0.60 | $3.05 | $0.13 | — | Yes | Yes | No | Apr 20, 2026 | |
| novita/kimi-k2.6 | 262K | 262K | $0.80 | $3.40 | $0.16 | — | Yes | Yes | No | Apr 20, 2026 | |
| azure-ai-foundry/grok-4-3 | 20K | 8K | $1.25 | $2.50 | $0.20 | — | Yes | Yes | No | Apr 17, 2026 | |
| xai/grok-4-3 | 1M | 1M | $1.25 | $2.50 | $0.20 | — | Yes | Yes | No | Apr 17, 2026 | |
| aws-bedrock/grok-4-3 | 1M | 131K | $1.25 | $2.50 | $0.20 | — | Yes | Yes | Yes | Apr 17, 2026 | |
| alibaba/qwen3.6-35b-a3b | 262K | 66K | $0.38 | $2.25 | — | — | Yes | Yes | No | Apr 17, 2026 | |
| novita/qwen3.6-35b-a3b | 262K | 64K | $0.25 | $1.49 | — | — | Yes | Yes | No | Apr 17, 2026 | |
| anthropic/claude-opus-4-7 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Apr 16, 2026 | |
| azure-anthropic/claude-opus-4-7 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Apr 16, 2026 | |
| aws-bedrock/claude-opus-4-7 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | No | Apr 16, 2026 | |
| vertex-anthropic/claude-opus-4-7 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Apr 16, 2026 | |
| xai/grok-build-0-1 | 256K | 256K | $1.00 | $2.00 | $0.20 | — | Yes | Yes | No | Apr 16, 2026 | |
| baidu/glm-5.1 | 203K | 131K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Apr 7, 2026 | |
| tencent/glm-5.1 | 200K | 128K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Apr 7, 2026 | |
| zai/glm-5.1 | 200K | 128K | $1.40 | $4.40 | $0.26 | — | Yes | Yes | No | Apr 7, 2026 | |
| embercloud/glm-5.1 | 203K | 131K | $0.93 | $2.93 | $0.17 | — | Yes | Yes | No | Apr 7, 2026 | |
| novita/glm-5.1 | 205K | 131K | $1.38 | $4.40 | $0.26 | — | Yes | Yes | No | Apr 7, 2026 | |
| deepinfra/gemma-4-26b-a4b-it | 262K | 33K | $0.07 | $0.34 | — | — | Yes | Yes | No | Apr 2, 2026 | |
| novita/gemma-4-26b-a4b-it | 262K | 33K | $0.13 | $0.40 | — | — | No | Yes | No | Apr 2, 2026 | |
| runware/gemma-4-31b-it | 262K | 66K | $0.10 | $0.30 | $0.01 | — | Yes | Yes | No | Apr 2, 2026 | |
| cerebras/gemma-4-31b-it | 131K | 33K | $0.99 | $1.49 | — | — | Yes | Yes | No | Apr 2, 2026 | |
| deepinfra/gemma-4-31b-it | 262K | 33K | $0.20 | $0.40 | — | — | Yes | Yes | No | Apr 2, 2026 | |
| consensusprotocol/gemma-4-31b-it | 262K | 33K | $0.10 | $0.25 | $0.01 | — | Yes | Yes | No | Apr 2, 2026 | |
| novita/gemma-4-31b-it | 262K | 33K | $0.14 | $0.40 | — | — | No | Yes | No | Apr 2, 2026 | |
| alibaba/qwen3.6-plus | 984K | 66K | $0.50 | $3.00 | $0.05 | $0.63 | Yes | Yes | No | Apr 2, 2026 | |
| tencent/glm-5v-turbo | 200K | 128K | $1.20 | $4.00 | $0.24 | — | Yes | Yes | No | Apr 1, 2026 | |
| bytedance/seed-2-0-code-preview-260328 | 262K | 131K | $0.50 | $3.00 | $0.10 | — | Yes | Yes | No | Mar 28, 2026 | |
| bytedance/seed-2-0-pro-260328 | 262K | 131K | $0.50 | $3.00 | $0.10 | — | Yes | Yes | Yes | Mar 28, 2026 | |
| minimax/minimax-m2.7 | 205K | 131K | $0.30 | $1.20 | $0.06 | — | Yes | Yes | No | Mar 18, 2026 | |
| scx-ai/minimax-m2.7 | 197K | 197K | $0.48 | $1.79 | $0.05 | — | Yes | Yes | No | Mar 18, 2026 | |
| tencent/minimax-m2.7 | 200K | 128K | $0.30 | $1.20 | $0.06 | — | Yes | Yes | No | Mar 18, 2026 | |
| gonka24/minimax-m2.7 | 205K | 131K | $0.08 | $0.32 | $0.02 | — | Yes | Yes | No | Mar 18, 2026 | |
| novita/minimax-m2.7 | 205K | 131K | $0.30 | $1.20 | $0.06 | — | Yes | Yes | No | Mar 18, 2026 | |
| minimax/minimax-m2.7-highspeed | 205K | 131K | $0.60 | $2.40 | $0.06 | — | Yes | Yes | No | Mar 18, 2026 | |
| openai/gpt-5.4-mini | 400K | 128K | $0.75 | $4.50 | $0.07 | — | Yes | Yes | Yes | Mar 17, 2026 | |
| azure/gpt-5.4-mini | 400K | 128K | $0.75 | $4.50 | $0.07 | — | Yes | Yes | Yes | Mar 17, 2026 | |
| openai/gpt-5.4-nano | 400K | 128K | $0.20 | $1.25 | $0.02 | — | Yes | Yes | Yes | Mar 17, 2026 | |
| azure/gpt-5.4-nano | 400K | 128K | $0.20 | $1.25 | $0.02 | — | Yes | Yes | Yes | Mar 17, 2026 | |
| tencent/glm-5-turbo | 200K | 128K | $1.20 | $4.00 | $0.24 | — | Yes | Yes | No | Mar 16, 2026 | |
| mistral/mistral-small-2603 | 262K | 256K | $0.15 | $0.60 | — | — | No | Yes | Yes | Mar 16, 2026 | |
| anthropic/claude-opus-4-6 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Mar 13, 2026 | |
| azure-anthropic/claude-opus-4-6 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Mar 13, 2026 | |
| aws-bedrock/claude-opus-4-6 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Mar 13, 2026 | |
| vertex-anthropic/claude-opus-4-6 | 1M | 128K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Mar 13, 2026 | |
| anthropic/claude-sonnet-4-6 | 1M | 64K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Mar 13, 2026 | |
| aws-bedrock/claude-sonnet-4-6 | 1M | 64K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Mar 13, 2026 | |
| vertex-anthropic/claude-sonnet-4-6 | 1M | 64K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Mar 13, 2026 | |
| xai/grok-4-20-beta-0309-non-reasoning | 2M | 30K | $2.00 | $6.00 | $0.20 | — | No | Yes | No | Mar 9, 2026 | |
| vertex-openai/grok-4-20-non-reasoning | 2M | 30K | $1.25 | $2.50 | $0.20 | — | No | Yes | No | Mar 9, 2026 | |
| xai/grok-4-20-beta-0309-reasoning | 2M | 30K | $2.00 | $6.00 | $0.20 | — | Yes | Yes | No | Mar 9, 2026 | |
| vertex-openai/grok-4-20-reasoning | 2M | 30K | $1.25 | $2.50 | $0.20 | — | Yes | Yes | No | Mar 9, 2026 | |
| openai/gpt-5.4 | 1.05M | 128K | $2.50 | $15.00 | $0.25 | — | Yes | Yes | Yes | Mar 5, 2026 | |
| azure/gpt-5.4 | 1.05M | 128K | $2.50 | $15.00 | $0.25 | — | Yes | Yes | Yes | Mar 5, 2026 | |
| openai/gpt-5.4-pro | 1.05M | 128K | $30.00 | $180 | — | — | Yes | Yes | No | Mar 5, 2026 | |
| azure/gpt-5.4-pro | 1.05M | 128K | $30.00 | $180 | — | — | Yes | Yes | No | Mar 5, 2026 | |
| google-ai-studio/gemini-pro-latest | 1.05M | 66K | $2.00 | $12.00 | $0.20 | — | Yes | Yes | Yes | Feb 27, 2026 | |
| alibaba/qwen3.5-122b-a10b | 262K | 66K | $0.40 | $3.20 | — | — | Yes | Yes | No | Feb 23, 2026 | |
| novita/qwen3.5-122b-a10b | 262K | 66K | $0.40 | $3.20 | — | — | Yes | Yes | No | Feb 23, 2026 | |
| alibaba/qwen3.5-27b | 262K | 66K | $0.30 | $2.40 | — | — | Yes | Yes | No | Feb 23, 2026 | |
| alibaba/qwen3.5-35b-a3b | 262K | 66K | $0.25 | $2.00 | — | — | Yes | Yes | No | Feb 23, 2026 | |
| deepinfra/qwen3.5-9b | 262K | 33K | $0.10 | $0.15 | — | — | Yes | Yes | Yes | Feb 23, 2026 | |
| quartz/gemini-3.1-pro-preview | 1.05M | 66K | $2.00 | $12.00 | $0.20 | — | Yes | Yes | Yes | Feb 19, 2026 | |
| google-vertex/gemini-3.1-pro-preview | 1.05M | 66K | $2.00 | $12.00 | $0.20 | — | Yes | Yes | Yes | Feb 19, 2026 | |
| google-ai-studio/gemini-3.1-pro-preview | 1.05M | 66K | $2.00 | $12.00 | $0.20 | — | Yes | Yes | Yes | Feb 19, 2026 | |
| alibaba/qwen35-397b-a17b | 262K | 66K | $0.60 | $3.60 | — | — | Yes | Yes | No | Feb 15, 2026 | |
| novita/qwen35-397b-a17b | 262K | 64K | $0.60 | $3.60 | — | — | Yes | Yes | No | Feb 15, 2026 | |
| minimax/minimax-m2.5-highspeed | 205K | 131K | $0.60 | $2.40 | $0.03 | — | Yes | Yes | No | Feb 13, 2026 | |
| alibaba/glm-5 | 203K | 16K | $0.57 | $2.58 | — | — | Yes | Yes | No | Feb 12, 2026 | |
| tencent/glm-5 | 200K | 128K | $1.00 | $3.20 | $0.20 | — | Yes | Yes | No | Feb 12, 2026 | |
| zai/glm-5 | 203K | 131K | $1.00 | $3.20 | $0.20 | — | Yes | Yes | No | Feb 12, 2026 | |
| embercloud/glm-5 | 203K | 131K | $0.72 | $2.30 | $0.14 | — | Yes | Yes | No | Feb 12, 2026 | |
| novita/glm-5 | 203K | 131K | $1.00 | $3.20 | $0.20 | — | Yes | Yes | No | Feb 12, 2026 | |
| minimax/minimax-m2.5 | 205K | 131K | $0.30 | $1.20 | $0.03 | — | Yes | Yes | No | Feb 12, 2026 | |
| novita/minimax-m2.5 | 205K | 131K | $0.30 | $1.20 | $0.03 | — | Yes | Yes | No | Feb 12, 2026 | |
| openai/gpt-5.3-codex | 400K | 128K | $1.75 | $14.00 | $0.17 | — | Yes | Yes | No | Feb 5, 2026 | |
| azure/gpt-5.3-codex | 400K | 128K | $1.75 | $14.00 | $0.17 | — | Yes | Yes | No | Feb 5, 2026 | |
| embercloud/qwen3-coder-next | 262K | 262K | $0.11 | $0.68 | $0.06 | — | No | Yes | No | Feb 3, 2026 | |
| alibaba/kimi-k2.5 | 262K | 98K | $0.57 | $3.01 | — | — | Yes | Yes | No | Jan 27, 2026 | |
| moonshot/kimi-k2.5 | 262K | 33K | $0.60 | $3.00 | $0.10 | — | Yes | Yes | No | Jan 27, 2026 | |
| embercloud/kimi-k2.5 | 262K | 262K | $0.41 | $1.98 | $0.23 | — | No | Yes | No | Jan 27, 2026 | |
| embercloud/glm-4.7-flash | 200K | 131K | $0.06 | $0.40 | $0.01 | — | No | Yes | No | Jan 19, 2026 | |
| zai/glm-4.7-flashx | 200K | 128K | $0.07 | $0.40 | $0.01 | — | Yes | Yes | No | Jan 19, 2026 | |
| minimax/minimax-m2.1 | 197K | 131K | $0.27 | $1.10 | — | — | Yes | Yes | No | Dec 23, 2025 | |
| novita/minimax-m2.1 | 205K | 131K | $0.30 | $1.20 | $0.03 | — | Yes | Yes | No | Dec 23, 2025 | |
| minimax/minimax-m2.1-lightning | 197K | 131K | $0.12 | $0.48 | — | — | Yes | Yes | No | Dec 23, 2025 | |
| bytedance/glm-4.7 | 200K | 128K | $0.60 | $2.20 | $0.11 | — | Yes | Yes | No | Dec 22, 2025 | |
| together-ai/glm-4.7 | 203K | 128K | $0.45 | $2.00 | — | — | Yes | No | No | Dec 22, 2025 | |
| zai/glm-4.7 | 200K | 128K | $0.60 | $2.20 | $0.11 | — | Yes | Yes | No | Dec 22, 2025 | |
| embercloud/glm-4.7 | 200K | 131K | $0.38 | $1.98 | $0.19 | — | Yes | Yes | No | Dec 22, 2025 | |
| cerebras/glm-4.7 | 200K | 128K | $2.25 | $2.75 | — | — | Yes | Yes | No | Dec 22, 2025 | |
| novita/glm-4.7 | 205K | 128K | $0.60 | $2.20 | $0.11 | — | Yes | Yes | No | Dec 22, 2025 | |
| bytedance/seed-1-8-251228 | 256K | 256K | $0.25 | $2.00 | $0.05 | — | Yes | Yes | No | Dec 18, 2025 | |
| google-vertex/gemini-3-flash-preview | 1.05M | 66K | $0.50 | $3.00 | $0.05 | — | Yes | Yes | Yes | Dec 17, 2025 | |
| google-ai-studio/gemini-3-flash-preview | 1.05M | 66K | $0.50 | $3.00 | $0.05 | — | Yes | Yes | Yes | Dec 17, 2025 | |
| openai/gpt-5.2 | 400K | 128K | $1.75 | $14.00 | $0.17 | — | Yes | Yes | Yes | Dec 11, 2025 | |
| azure/gpt-5.2 | 400K | 128K | $1.75 | $14.00 | $0.17 | — | Yes | Yes | Yes | Dec 11, 2025 | |
| azure/gpt-5.2-codex | 400K | 128K | $1.75 | $14.00 | $0.17 | — | Yes | Yes | No | Dec 11, 2025 | |
| openai/gpt-5.2-pro | 400K | 272K | $21.00 | $168 | — | — | Yes | Yes | No | Dec 11, 2025 | |
| mistral/devstral-2512 | 262K | 262K | $0.40 | $2.00 | — | — | No | No | No | Dec 9, 2025 | |
| zai/glm-4.6v | 128K | 16K | $0.30 | $0.90 | $0.05 | — | Yes | Yes | No | Dec 8, 2025 | |
| novita/glm-4.6v | 131K | 16K | $0.30 | $0.90 | $0.06 | — | Yes | Yes | No | Dec 8, 2025 | |
| zai/glm-4.6v-flashx | 128K | 16K | $0.04 | $0.40 | $0.004 | — | Yes | Yes | No | Dec 8, 2025 | |
| mistral/ministral-14b-2512 | 262K | 262K | $0.20 | $0.20 | — | — | No | No | No | Dec 2, 2025 | |
| mistral/ministral-8b-2512 | 262K | 262K | $0.15 | $0.15 | — | — | No | No | No | Dec 2, 2025 | |
| mistral/ministral-3b-2512 | 131K | 131K | $0.10 | $0.10 | — | — | No | No | No | Dec 2, 2025 | |
| mistral/mistral-large-latest | 128K | 262K | $4.00 | $12.00 | — | — | No | No | No | Dec 2, 2025 | |
| mistral/mistral-large-2512 | 262K | 262K | $0.50 | $1.50 | — | — | No | No | No | Dec 2, 2025 | |
| bytedance/deepseek-v3.2 | 131K | 33K | $0.28 | $0.42 | $0.06 | — | Yes | Yes | No | Dec 1, 2025 | |
| deepinfra/deepseek-v3.2 | 160K | 66K | $0.26 | $0.38 | $0.13 | — | No | Yes | No | Dec 1, 2025 | |
| novita/deepseek-v3.2 | 164K | 66K | $0.27 | $0.40 | $0.13 | — | Yes | Yes | No | Dec 1, 2025 | |
| anthropic/claude-opus-4-5-20251101 | 200K | 32K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Nov 24, 2025 | |
| aws-bedrock/claude-opus-4-5-20251101 | 200K | 32K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Nov 24, 2025 | |
| vertex-anthropic/claude-opus-4-5-20251101 | 200K | 32K | $5.00 | $25.00 | $0.50 | $6.25 | Yes | Yes | Yes | Nov 24, 2025 | |
| azure-ai-foundry/grok-4-1-fast-reasoning | 2M | 30K | $0.20 | $0.50 | — | — | Yes | Yes | No | Nov 19, 2025 | |
| azure-ai-foundry/grok-4-1-fast-non-reasoning | 2M | 30K | $0.20 | $0.50 | — | — | No | Yes | No | Nov 19, 2025 | |
| openai/gpt-5.1 | 400K | 128K | $1.25 | $10.00 | $0.13 | — | Yes | Yes | Yes | Nov 13, 2025 | |
| azure/gpt-5.1 | 400K | 128K | $1.25 | $10.00 | $0.13 | — | Yes | Yes | Yes | Nov 13, 2025 | |
| azure/gpt-5.1-codex | 400K | 272K | $1.25 | $10.00 | — | — | Yes | Yes | No | Nov 13, 2025 | |
| azure/gpt-5.1-codex-mini | 400K | 128K | $0.25 | $2.00 | $0.03 | — | Yes | Yes | No | Nov 13, 2025 | |
| minimax/minimax-m2 | 197K | 131K | $0.20 | $1.00 | $0.03 | — | Yes | Yes | No | Oct 27, 2025 | |
| anthropic/claude-haiku-4-5-20251001 | 200K | 64K | $1.00 | $5.00 | $0.10 | $1.25 | Yes | Yes | Yes | Oct 15, 2025 | |
| aws-bedrock/claude-haiku-4-5-20251001 | 200K | 64K | $1.00 | $5.00 | $0.10 | $1.25 | Yes | Yes | Yes | Oct 15, 2025 | |
| anthropic/claude-haiku-4-5 | 200K | 64K | $1.00 | $5.00 | $0.10 | $1.25 | Yes | Yes | Yes | Oct 15, 2025 | |
| aws-bedrock/claude-haiku-4-5 | 200K | 64K | $1.00 | $5.00 | $0.10 | $1.25 | Yes | Yes | Yes | Oct 15, 2025 | |
| vertex-anthropic/claude-haiku-4-5 | 200K | 64K | $1.00 | $5.00 | $0.10 | $1.25 | Yes | Yes | Yes | Oct 15, 2025 | |
| openai/gpt-5-pro | 400K | 272K | $15.00 | $120 | — | — | Yes | Yes | Yes | Oct 6, 2025 | |
| deepinfra/qwen3-vl-30b-a3b-instruct | 262K | 33K | $0.15 | $0.60 | — | — | No | Yes | No | Oct 4, 2025 | |
| novita/qwen3-vl-30b-a3b-instruct | 131K | 33K | $0.20 | $0.70 | — | — | No | Yes | No | Oct 4, 2025 | |
| zai/glm-4.6 | 200K | 131K | $0.60 | $2.20 | $0.11 | — | Yes | Yes | No | Sep 30, 2025 | |
| novita/glm-4.6 | 205K | 131K | $0.55 | $2.20 | $0.11 | — | Yes | Yes | No | Sep 30, 2025 | |
| anthropic/claude-sonnet-4-5-20250929 | 200K | 64K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Sep 29, 2025 | |
| aws-bedrock/claude-sonnet-4-5-20250929 | 200K | 8K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Sep 29, 2025 | |
| anthropic/claude-sonnet-4-5 | 200K | 64K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Sep 29, 2025 | |
| aws-bedrock/claude-sonnet-4-5 | 200K | 8K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Sep 29, 2025 | |
| vertex-anthropic/claude-sonnet-4-5 | 200K | 64K | $3.00 | $15.00 | $0.30 | $3.75 | Yes | Yes | Yes | Sep 29, 2025 | |
| novita/qwen3-max | 262K | 66K | $0.84 | $3.38 | — | — | No | Yes | No | Sep 23, 2025 | |
| deepinfra/qwen3-vl-235b-a22b-instruct | 262K | 33K | $0.20 | $0.88 | $0.11 | — | No | Yes | No | Sep 23, 2025 | |
| novita/qwen3-vl-235b-a22b-instruct | 131K | 33K | $0.30 | $1.50 | — | — | No | Yes | No | Sep 23, 2025 | |
| novita/qwen3-vl-235b-a22b-thinking | 131K | 33K | $0.98 | $3.95 | — | — | Yes | No | No | Sep 23, 2025 | |
| alibaba/qwen3-vl-plus | 262K | 33K | $0.20 | $1.60 | $0.04 | $0.25 | No | No | No | Sep 23, 2025 | |
| bytedance/seed-1-6-250915 | 256K | 256K | $0.25 | $2.00 | $0.05 | — | Yes | Yes | No | Sep 15, 2025 | |
| alibaba/qwen-plus | 131K | 32K | $0.40 | $1.20 | $0.08 | $0.50 | No | Yes | No | Sep 11, 2025 | |
| perplexity/sonar | 130K | 4K | $0.25 | $2.50 | — | $0.25 | No | No | Yes | Sep 1, 2025 | |
| novita/qwen3-next-80b-a3b-instruct | 131K | 33K | $0.15 | $1.50 | — | — | No | Yes | No | Sep 2025 | |
| zai/glm-4.5v | 128K | 16K | $0.60 | $1.80 | $0.11 | — | Yes | Yes | No | Aug 11, 2025 | |
| novita/glm-4.5v | 66K | 16K | $0.60 | $1.80 | $0.11 | — | Yes | Yes | No | Aug 11, 2025 | |
| openai/gpt-5 | 400K | 128K | $1.25 | $10.00 | $0.13 | — | Yes | Yes | Yes | Aug 7, 2025 | |
| azure/gpt-5 | 400K | 128K | $1.25 | $10.00 | $0.13 | — | Yes | Yes | Yes | Aug 7, 2025 | |
| openai/gpt-5-mini | 400K | 128K | $0.25 | $2.00 | $0.03 | — | Yes | Yes | Yes | Aug 7, 2025 | |
| azure/gpt-5-mini | 400K | 128K | $0.25 | $2.00 | $0.03 | — | Yes | Yes | Yes | Aug 7, 2025 | |
| openai/gpt-5-nano | 400K | 128K | $0.05 | $0.40 | $0.005 | — | Yes | Yes | Yes | Aug 7, 2025 | |
| azure/gpt-5-nano | 400K | 128K | $0.05 | $0.40 | $0.005 | — | Yes | Yes | Yes | Aug 7, 2025 | |
| bytedance/gpt-oss-120b | 128K | 32K | $0.10 | $0.50 | $0.02 | — | Yes | Yes | No | Aug 5, 2025 | |
| groq/gpt-oss-120b | 131K | 33K | $0.15 | $0.75 | — | — | Yes | Yes | No | Aug 5, 2025 | |
| scx-ai/gpt-oss-120b | 131K | 33K | $0.17 | $0.55 | — | — | Yes | Yes | No | Aug 5, 2025 | |
| together-ai/gpt-oss-120b | 131K | 33K | $0.15 | $0.60 | — | — | Yes | Yes | No | Aug 5, 2025 | |
| runware/gpt-oss-120b | 131K | 33K | $0.03 | $0.14 | $0.03 | — | Yes | Yes | No | Aug 5, 2025 | |
| azure/gpt-oss-120b | 131K | 33K | $0.15 | $0.60 | — | — | Yes | Yes | No | Aug 5, 2025 | |
| cerebras/gpt-oss-120b | 131K | 33K | $0.35 | $0.75 | — | — | Yes | Yes | No | Aug 5, 2025 | |
| groq/gpt-oss-20b | 131K | 33K | $0.10 | $0.50 | — | — | Yes | Yes | No | Aug 5, 2025 | |
| consensusprotocol/gpt-oss-20b | 128K | 33K | $0.04 | $0.19 | $0.01 | — | Yes | Yes | No | Aug 5, 2025 | |
| novita/qwen3-coder-30b-a3b-instruct | 160K | 33K | $0.07 | $0.27 | — | — | No | Yes | No | Jul 31, 2025 | |
| mistral/codestral-2508 | 256K | 256K | $0.30 | $0.90 | — | — | No | No | No | Jul 30, 2025 | |
| zai/glm-4.5 | 128K | 98K | $0.60 | $2.20 | $0.11 | — | Yes | Yes | No | Jul 28, 2025 | |
| embercloud/glm-4.5 | 131K | 96K | $0.60 | $2.20 | $0.11 | — | No | Yes | No | Jul 28, 2025 | |
| zai/glm-4.5-airx | 128K | 128K | $1.10 | $4.50 | $0.22 | — | No | Yes | No | Jul 28, 2025 | |
| zai/glm-4.5-x | 128K | 128K | $2.20 | $8.90 | $0.45 | — | Yes | Yes | No | Jul 28, 2025 | |
| zai/glm-4.5-air | 128K | 98K | $0.20 | $1.10 | $0.03 | — | No | Yes | No | Jul 28, 2025 | |
| embercloud/glm-4.5-air | 131K | 96K | $0.13 | $0.85 | $0.03 | — | No | Yes | No | Jul 28, 2025 | |
| alibaba/qwen-flash | 1M | 32K | $0.05 | $0.40 | $0.01 | $0.06 | No | Yes | No | Jul 28, 2025 | |
| alibaba/qwen3-coder-flash | 998K | 66K | $0.30 | $1.50 | $0.06 | $0.38 | No | Yes | No | Jul 28, 2025 | |
| bytedance/seed-1-6-flash-250715 | 256K | 256K | $0.07 | $0.30 | $0.01 | — | Yes | Yes | No | Jul 26, 2025 | |
| novita/qwen3-235b-a22b-thinking-2507 | 131K | 33K | $0.30 | $3.00 | — | — | No | Yes | No | Jul 25, 2025 | |
| novita/qwen3-coder-480b-a35b-instruct | 262K | 66K | $0.38 | $1.55 | — | — | No | Yes | No | Jul 22, 2025 | |
| cerebras/qwen3-235b-a22b-instruct-2507 | 262K | 8K | $0.60 | $1.20 | — | — | No | Yes | No | Jul 21, 2025 | |
| novita/qwen3-235b-a22b-instruct-2507 | 131K | 16K | $0.09 | $0.58 | — | — | No | Yes | No | Jul 21, 2025 | |
| novita/kimi-k2 | 131K | 131K | $0.57 | $2.30 | — | — | No | Yes | No | Jul 11, 2025 | |
| xai/grok-4 | 256K | 256K | $3.00 | $15.00 | $0.75 | — | Yes | Yes | No | Jul 9, 2025 | |
| novita/ernie-4.5-vl-424b-a47b | 123K | 16K | $0.42 | $1.25 | — | — | Yes | No | No | Jun 30, 2025 | |
| bytedance/seed-1-6-250615 | 256K | 256K | $0.25 | $2.00 | $0.05 | — | Yes | Yes | No | Jun 25, 2025 | |
| mistral/mistral-small-2506 | 128K | 16K | $0.10 | $0.30 | — | — | No | No | No | Jun 20, 2025 | |
| greenference/qwen3-14b | 16K | 8K | $0.08 | $0.23 | — | — | No | Yes | Yes | Apr 28, 2025 | |
| novita/qwen3-235b-a22b-fp8 | 41K | 20K | $0.20 | $0.80 | — | — | No | No | No | Apr 28, 2025 | |
| greenference/qwen3-30b-a3b | 8K | 4K | $0.10 | $0.28 | — | — | No | No | Yes | Apr 28, 2025 | |
| scx-ai/qwen3-32b | 33K | 8K | $0.36 | $0.87 | — | — | Yes | Yes | No | Apr 28, 2025 | |
| openai/o3 | 200K | 100K | $2.00 | $8.00 | $0.50 | — | No | No | Yes | Apr 16, 2025 | |
| zai/glm-4-32b-0414-128k | 128K | 128K | $0.10 | $0.10 | — | — | No | Yes | No | Apr 14, 2025 | |
| openai/gpt-4.1 | 1M | 33K | $2.00 | $8.00 | $0.50 | — | No | Yes | Yes | Apr 14, 2025 | |
| azure/gpt-4.1 | 1M | 33K | $2.00 | $8.00 | $0.50 | — | No | Yes | Yes | Apr 14, 2025 | |
| openai/gpt-4.1-mini | 1M | 33K | $0.40 | $1.60 | $0.10 | — | No | Yes | Yes | Apr 14, 2025 | |
| azure/gpt-4.1-mini | 1M | 33K | $0.40 | $1.60 | $0.10 | — | No | Yes | Yes | Apr 14, 2025 | |
| aws-bedrock/llama-4-maverick-17b-instruct | 8K | 2K | $0.24 | $0.97 | — | — | No | No | No | Apr 5, 2025 | |
| novita/llama-4-maverick-17b-instruct | 1.05M | 8K | $0.27 | $0.85 | — | — | No | No | No | Apr 5, 2025 | |
| aws-bedrock/llama-4-scout-17b-instruct | 8K | 2K | $0.17 | $0.66 | — | — | No | No | No | Apr 5, 2025 | |
| novita/llama-4-scout-17b-instruct | 131K | 131K | $0.18 | $0.59 | — | — | No | No | No | Apr 5, 2025 | |
| openai/gpt-4o-mini-transcribe | 16K | 2K | $1.25 | $5.00 | — | — | No | No | No | Mar 20, 2025 | |
| openai/gpt-4o-transcribe | 16K | 2K | $2.50 | $10.00 | — | — | No | No | No | Mar 20, 2025 | |
| alibaba/qwen-max | 33K | 8K | $1.60 | $6.40 | — | — | No | Yes | No | Jan 25, 2025 | |
| minimax/minimax-text-01 | 1M | 131K | $0.20 | $1.10 | — | — | Yes | Yes | No | Jan 15, 2025 | |
| cerebras/llama-3.3-70b-instruct | 128K | 4K | $0.85 | $1.20 | — | — | No | Yes | No | Dec 6, 2024 | |
| novita/llama-3.3-70b-instruct | 131K | 120K | $0.14 | $0.40 | — | — | No | Yes | No | Dec 6, 2024 | |
| inference.net/llama-3.2-11b-instruct | 128K | 128K | $0.07 | $0.33 | — | — | No | No | No | Sep 25, 2024 | |
| novita/llama-3.2-3b-instruct | 33K | 32K | $0.03 | $0.05 | — | — | No | No | No | Sep 18, 2024 | |
| alibaba/qwen-plus-latest | 1M | 32K | $0.40 | $1.20 | $0.08 | $0.50 | No | Yes | No | Sep 9, 2024 | |
| openai/gpt-4o | 128K | 16K | $2.50 | $10.00 | $1.25 | — | No | Yes | Yes | Aug 6, 2024 | |
| azure/gpt-4o | 128K | 16K | $2.50 | $10.00 | $1.25 | — | No | Yes | No | Aug 6, 2024 | |
| aws-bedrock/llama-3.1-70b-instruct | 128K | 2K | $0.72 | $0.72 | — | — | No | No | No | Jul 23, 2024 | |
| openai/gpt-4o-mini | 128K | 16K | $0.15 | $0.60 | $0.07 | — | No | Yes | Yes | Jul 18, 2024 | |
| novita/llama-3-70b-instruct | 8K | 8K | $0.51 | $0.74 | — | — | No | No | No | Apr 18, 2024 |