minimax/minimax-m2.7
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.250 | $1.00 | 197K | 100% |
| Novitafp8 | $0.270 | $1.08 | 205K | 99.9% |
| Morph | $0.279 | $1.20 | 197K | 97.9% |
| Fireworks | $0.300 | $1.20 | 197K | 99.9% |
| Togetherfp4 | $0.300 | $1.20 | 197K | 100% |
| Minimaxfp8 | $0.300 | $1.20 | 205K | 99% |
| Mara | $0.300 | $1.20 | 197K | 91.7% |
| Minimaxfp8 | $0.600 | $2.40 | 205K | 94.7% |
| SambaNova | $0.600 | $2.40 | 197K | 99.3% |
| SambaNova | $1.20 | $4.80 | 197K | 88.7% |
MiniMax M2.7 costs $0.250 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 108th cheapest of 298 paid models.
MiniMax M2.7 scores 49.6 on the Artificial Analysis Intelligence Index, ranking 15th of 178 benchmarked models, with a GPQA Diamond score of 87%.
MiniMax M2.7 generates around 261 tokens per second with 562ms time-to-first-token (p50), the 11th fastest tracked model.
MiniMax M2.7 supports a 205K-token context window and can output up to 131K tokens. It accepts text input.