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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Inceptronfp8 | $0.150 | $0.900 | 197K | 99.9% |
| AkashMLfp8 | $0.150 | $1.15 | 197K | 99.6% |
| DeepInfrafp8 | $0.150 | $1.15 | 197K | 100% |
| Chutesfp8 | $0.150 | $1.20 | 197K | 100% |
| Phala | $0.200 | $1.38 | 197K | 100% |
| DigitalOcean | $0.225 | $0.900 | 200K | 100% |
| StreamLake | $0.270 | $1.08 | 200K | — |
| AtlasCloudfp8 | $0.295 | $1.20 | 197K | — |
| Mara | $0.300 | $1.20 | 197K | — |
| Friendli | $0.300 | $1.20 | 197K | 100% |
| Minimaxfp8 | $0.300 | $1.20 | 205K | 100% |
| Novitafp8 | $0.300 | $1.20 | 205K | — |
| SiliconFlowfp8 | $0.300 | $1.20 | 197K | — |
| Parasailfp8 | $0.300 | $1.20 | 197K | 99.3% |
| WandBfp8 | $0.300 | $1.20 | 197K | — |
| Venice | $0.340 | $1.19 | 198K | — |
| Minimaxfp8 | $0.600 | $2.40 | 205K | — |
MiniMax M2.5 costs $0.150 per million input tokens and $0.900 per million output tokens via OpenRouter, making it 79th cheapest of 298 paid models.
MiniMax M2.5 scores 41.9 on the Artificial Analysis Intelligence Index, ranking 37th of 180 benchmarked models, with a GPQA Diamond score of 85%.
MiniMax M2.5 generates around 199 tokens per second with 521ms time-to-first-token (p50), the 17th fastest tracked model.
MiniMax M2.5 supports a 205K-token context window and can output up to 197K tokens. It accepts text input.