MiniMax M2.5 is SOTA in coding, agentic tool use and search, office work, and a range of other economically valuable tasks, boasting scores of 80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp (with context management).
function_callinghttps://api.deepinfra.com/v1/openai/v1/chat/completions| Model | Context | Max out | Pricing |
|---|---|---|---|
| MiniMax-M2.5 | 197K | — | $0.15$1.15 |
| MiniMax-M2.7 | 197K | — | $0.25$1 |
| MiniMax-M3 | 524K | — | $0.28$1.1 |
| MiniMax-M2.7-Turbo | 197K | — | $0.38$1.7 |
/v1/models/deepinfra/MiniMaxAI/MiniMax-M2.5