Models
Every model the gateway can call today, with billed prices per million tokens. Use the id as model in a request or in an endpoint.
50 models
| Max output | Supports | |||||
|---|---|---|---|---|---|---|
| qwen-flash | Alibaba | $0.063 | $0.50 | 1M | 1M | text |
| qwen-plus | Alibaba | $0.50 | $1.50 | 1M | 1M | text |
| qwen3.8-flash | Alibaba | $0.188 | $0.588 | 1M | 128K | text |
| qwen3.8-max | Alibaba | $2.50 | $7.50 | 1M | 128K | text |
| claude-opus-4-6 | Anthropic | $6.25 | $31.25 | 1M | 128K | text |
| claude-opus-4-7 | Anthropic | $6.25 | $31.25 | 1M | 128K | text |
| claude-opus-4-8 | Anthropic | $6.25 | $31.25 | 1M | 128K | text |
| claude-opus-5 | Anthropic | $6.25 | $31.25 | 1M | 128K | text |
| claude-sonnet-4-5-20250929 | Anthropic | $3.75 | $18.75 | 200K | 64K | text |
| claude-sonnet-4-6 | Anthropic | $3.75 | $18.75 | 1M | 128K | text |
| deepseek-v4-flash | DeepSeek | $0.175 | $0.35 | 1M | 384K | text |
| deepseek-v4-pro | DeepSeek | $0.544 | $1.09 | 1M | 384K | text |
| gemini-2.5-flash | $0.375 | $3.13 | 1M | 66K | text | |
| gemini-2.5-flash-lite | $0.125 | $0.50 | 1M | 66K | text | |
| gemini-2.5-pro | $1.56 | $12.50 | 1M | 66K | text | |
| gemini-3.1-flash-lite | $0.313 | $1.88 | 1M | 66K | text | |
| gemini-3.1-pro-preview | $2.50 | $15.00 | 1M | 66K | text | |
| gemini-3.5-flash | $1.88 | $11.25 | 1M | 66K | text | |
| gemini-3.5-flash-lite | $0.375 | $3.13 | 1M | 66K | text | |
| gemini-3.6-flash | $1.88 | $9.38 | 1M | 66K | text | |
| gemini-3.7-flash | $0.938 | $4.69 | 1M | 66K | text | |
| gemini-3.8-flash | $0.938 | $4.69 | 1M | 66K | textvisionaudio_inputvideo_inputfunction_callingstructured_outputreasoning_effortprompt_caching | |
| grok-4-0709 | Grok | $3.75 | $18.75 | 256K | 256K | text |
| grok-4-fast-non-reasoning | Grok | $0.25 | $0.625 | 2M | 2M | text |
| grok-4-fast-reasoning | Grok | $0.25 | $0.625 | 2M | 2M | text |
| grok-4.5 | Grok | $2.50 | $7.50 | 500K | 500K | text |
| grok-4.6 | Grok | $2.50 | $7.50 | 256K | 256K | text |
| grok-4.7 | Grok | $2.50 | $7.50 | 256K | 256K | textvisionfunction_callingstructured_output |
| ministral-8b-2410 | Mistral | $0.125 | $0.125 | 128K | 8K | text |
| mistral-large-2512 | Mistral | $0.625 | $1.88 | 262K | 262K | text |
| mistral-medium-2508 | Mistral | $0.50 | $2.50 | 128K | 8K | text |
| mistral-small-2506 | Mistral | $0.25 | $0.75 | 128K | 8K | text |
| gpt-4 | OpenAI | $37.50 | $75.00 | 8K | 8K | textassistance |
| gpt-4.1-mini | OpenAI | $0.50 | $2.00 | 128K | 16K | text |
| gpt-4o | OpenAI | $3.13 | $12.50 | 128K | 16K | textassistance |
| gpt-4o-minidefault | OpenAI | $0.188 | $0.75 | 128K | 16K | textassistance |
| gpt-5 | OpenAI | $1.56 | $12.50 | 272K | 128K | text |
| gpt-5-mini | OpenAI | $0.313 | $2.50 | 272K | 128K | text |
| gpt-5-nano | OpenAI | $0.063 | $0.50 | 272K | 128K | text |
| gpt-5.1 | OpenAI | $1.56 | $12.50 | 272K | 128K | text |
| gpt-5.2 | OpenAI | $2.19 | $17.50 | 272K | 128K | text |
| gpt-5.4 | OpenAI | $3.13 | $18.75 | 1.1M | 128K | text |
| gpt-5.4-mini | OpenAI | $0.938 | $5.63 | 400K | 128K | text |
| gpt-5.4-nano | OpenAI | $0.25 | $1.56 | 400K | 128K | text |
| gpt-5.6-luna | OpenAI | $0.25 | $1.50 | 1.1M | 128K | text |
| gpt-5.6-sol | OpenAI | $6.25 | $37.50 | 1.1M | 128K | text |
| gpt-5.6-terra | OpenAI | $2.50 | $15.00 | 1.1M | 128K | text |
| o1 | OpenAI | $18.75 | $75.00 | 200K | 100K | text |
| o3-mini | OpenAI | $1.38 | $5.50 | 200K | 100K | text |
| o3-mini-2025-01-31 | OpenAI | $1.38 | $5.50 | 200K | 100K | text |
Plus auto: send model "auto" and the gateway picks among your routing candidates.