MiniMax-M2.7
nvidia/minimaxai/minimax-m2.7 · family minimax · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#390 of 7,708
Cheapest rank
- Provider
- Nvidia (
nvidia) - Kind
- text (outputs text)
- Context
- 204,800 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“MiniMax-M2.7” is offered by 36 providers — cheapest-effective first. This one (Nvidia) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia (this) | free | free | $0.00 | 205k |
| MiniMax Token Plan (minimax.io) | free | free | $0.00 | 205k |
| MiniMax Token Plan (minimax.cn) | free | free | $0.00 | 205k |
| UnoRouter | free | free | $0.00 | 205k |
| SCNet Token Plan | free | free | $0.00 | 205k |
| Kenari | free | free | $0.00 | 205k |
| DevPass (LLM Gateway) | $0.08 | $0.32 | $0.14 | 205k |
| Deep Infra | $0.25 | $1 | $0.44 | 197k |
| Pioneer | $0.279 | $1.2 | $0.51 | 205k |
| Ollama Cloud | $0.3 | $1.2 | $0.52 | 197k |
| Kilo Gateway | $0.3 | $1.2 | $0.52 | 205k |
| Abacus | $0.3 | $1.2 | $0.52 | 205k |
| 302.AI | $0.3 | $1.2 | $0.52 | 205k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Nvidia 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):