MiniMax M2.7
empiriolabs/minimax-m2-7 · family minimax · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.26
Blended $/1M (3:1)
$0.15
Input $/1M
$0.6
Output $/1M
$0.75
1M in + 1M out
$0.03 −80%
Cache read $/1M
#2182 of 8,539
Cheapest rank
- Provider
- EmpirioLabs AI (
empiriolabs) - 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 7 providers — cheapest-effective first. This one (EmpirioLabs AI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| EmpirioLabs AI (this) | $0.15 | $0.6 | $0.26 | 205k |
| NanoGPT | $0.21 | $0.84 | $0.37 | 205k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.52 | 205k |
| Merge Gateway | $0.3 | $1.2 | $0.52 | 205k |
| ZenMux | $0.3 | $1.2 | $0.52 | 205k |
| AIHubMix | $0.3 | $1.2 | $0.52 | 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 EmpirioLabs AI 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):