MiniMax: MiniMax M2.5
minimax/minimax-m2.5
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...
Modalities
In / Out Price
$0.27 / $1.08 per 1M
Context
205K
Released
Feb 12, 2026
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Venice | 198K | $0.27 | $0.95 | $0.03 | — | — | 100.00% |
 StreamLake | 200K | $0.27 | $1.08 | $0.027 | — | — | 100.00% |
 AtlasCloudfp8 | 197K | $0.295 | $1.20 | $0.06 | — | — | 100.00% |
 GMICloudfp8 | 197K | $0.30 | $1.20 | $0.03 | — | — | 100.00% |
 DigitalOcean | 66K | $0.30 | $1.20 | $0.06 | — | — | 100.00% |
 Friendli | 197K | $0.30 | $1.20 | $0.06 | — | — | 100.00% |
 Novitafp8 | 205K | $0.30 | $1.20 | $0.03 | — | — | 100.00% |
| Minimaxfp8 | 205K | $0.30 | $1.20 | $0.03 | — | — | — |
| Minimaxfp8 | 205K | $0.60 | $2.40 | $0.06 | — | — | 100.00% |