deepinfra/MiniMaxAI/MiniMax-M2.7 · family minimax · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.
deepinfra)“MiniMax-M2.7” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 205k |
| UnoRouter | free | free | $0.00 | 205k |
| MiniMax Token Plan (minimax.io) | free | free | $0.00 | 205k |
| MiniMax Token Plan (minimaxi.com) | free | free | $0.00 | 205k |
| LLM Gateway | $0.08 | $0.32 | $0.14 | 205k |
| Deep Infra (this) | $0.25 | $1 | $0.44 | 197k |
| Pioneer | $0.279 | $1.2 | $0.51 | 205k |
| Fireworks AI | $0.3 | $1.2 | $0.52 | 197k |
| OpenCode Go | $0.3 | $1.2 | $0.52 | 205k |
jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Deep Infra and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"MiniMaxAI/MiniMax-M2.7","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):