MiniMax M2.7
aihubmix/minimax-m2.7 · family minimax · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.52
Blended $/1M (3:1)
$0.3
Input $/1M
$1.2
Output $/1M
$1.50
1M in + 1M out
$0.06 −80%
Cache read $/1M
#2908 of 7,708
Cheapest rank
- Provider
- AIHubMix (
aihubmix) - Kind
- text (outputs text)
- Context
- 204,800 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“MiniMax M2.7” is offered by 8 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.26 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| EmpirioLabs AI | $0.15 | $0.6 | $0.26 | 200k |
| AIHubMix (this) | $0.3 | $1.2 | $0.52 | 205k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.52 | 205k |
| NovitaAI | $0.3 | $1.2 | $0.52 | 205k |
| Merge Gateway | $0.3 | $1.2 | $0.52 | 205k |
| ZenMux | $0.3055 | $1.22 | $0.53 | 205k |
| NanoGPT | $0.315 | $1.26 | $0.55 | 205k |
| Venice AI | $0.375 | $1.5 | $0.66 | 198k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at AIHubMix and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"minimax-m2.7","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):