MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.
Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.
| Charge | Agents | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.32 | $0.30 | per 1M tokens |
| Outputper 1M tokens | $1.30 | $1.19 | per 1M tokens |
| Cached inputper 1M tokens | $0.032 | $0.030 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.32 in and $1.30 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| Venice, answering | 94.8% | 198K |
| StreamLake, answering | 99.7% | 200K |
| AtlasCloudFp8fp8, answering | 99.6% | 197K |
| DigitalOcean, answering | 99.9% | 66K |
| Friendli, answering | 100% | 197K |
| NovitaFp8fp8, answering | 99.8% | 205K |
| MinimaxFp8fp8, answering | 99.8% | 205K |
| MinimaxHighspeedfp8, answering | 99.7% | 205K |