Models / MiniMax / MiniMax-M2.7-highspeed
MiniMax · minimax
MiniMax-M2.7-highspeed
Low-latency M2.7 variant for interactive coding plans and agent loops
$0.60 in · $2.40 out
per 1M tokens · first-party price. Reference price from MiniMax, the lab's own listing.
Provider input prices run from $0.30 to $0.60 per 1M tokens. Output prices run from $1.20 to $2.40.
- Context
- 204,800
- Max output
- 131,072
- Cache read
- $0.06
- Cache write
- $0.38
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Unknown
- Vision
- No
- Open weights
- Yes
- License
- —
- Released
- Mar 18, 2026
- Updated in source
- Mar 18, 2026
- Knowledge
- —
- Providers
- 14
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| EmpirioLabs AI | $0.30 | $1.20 | $0.03 | — | — |
| Auriko | $0.60 | $2.40 | — | $0.38 | — |
| DevPass | $0.60 | $2.40 | $0.06 | $0.38 | — |
| FastRouter | $0.60 | $2.40 | — | — | — |
| LLM Gateway | $0.60 | $2.40 | $0.06 | — | — |
| Merge Gateway | $0.60 | $2.40 | $0.06 | $0.38 | — |
| MiniMaxreference | $0.60 | $2.40 | $0.06 | $0.38 | — |
| Novita AI | $0.60 | $2.40 | $0.06 | $0.38 | — |
| Ofox | $0.60 | $2.40 | $0.06 | $0.38 | — |
| OrcaRouter | $0.60 | $2.40 | $0.06 | $0.38 | — |
| Requesty | $0.60 | $2.40 | $0.06 | $1.20 | — |
| Tempr Gateway | $0.60 | $2.40 | $0.06 | $0.38 | — |
| Vercel AI Gateway | $0.60 | $2.40 | $0.06 | $0.38 | — |
| Kenari | $0 | $0 | — | — | — |