MiniMax
MiniMax M2.5
minimax/minimax-m2.5
Input
$0.30
per 1M tokens
Output
$1.20
per 1M tokens
Cached input
$0.03
per 1M tokens
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
- Released
- Context window
- 205K tokens
- Max output
- 131K tokens
- Input
- text
- Output
- text
- Reasoning
- Yes
Price history
- input $0.27 → $0.30 +11% · output $0.95 → $1.20 +26%
Providers on OpenRouter
8 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| Venice | $0.27 | $0.95 | 198K | 100% | 96.8% |
| StreamLake | $0.27 | $1.08 | 200K | — | 100% |
| AtlasCloudfp8 | $0.295 | $1.20 | 197K | — | 100% |
| DigitalOcean | $0.30 | $1.20 | 66K | 100% | 100% |
| GMICloudfp8 | $0.30 | $1.20 | 197K | 100% | 98.8% |
| Minimaxvendor's own | $0.30 | $1.20 | 205K | — | 97.2% |
| Novitafp8 | $0.30 | $1.20 | 205K | — | 94.9% |
| Minimaxhighspeedvendor's own | $0.60 | $2.40 | 205K | 100% | 84.2% |