9models tracked · ranked by intelligence, speed & price
MiniMax's smartest model is MiniMax M3 (44.4 on the Intelligence Index), and its cheapest is MiniMax M3 (batch) at $0.150 per million input tokens. All 9 MiniMax models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| minimax-m3 ReasoningToolsJSON+1 | 44.4 | — | — | $0.300 | 1.0M |
| minimax-m3:batch ReasoningToolsJSON+1 | 44.4 | — | — | $0.150 | 524K |
| minimax-m2.7 ReasoningToolsJSON | 38.1 | — | — | $0.250 | 205K |
| minimax-m2.5 ReasoningToolsJSON | 33.7 | — | — | $0.150 | 205K |
| minimax-m2.1 ReasoningToolsJSON | 31.4 | — | — | $0.300 | 205K |
| minimax-m2 ReasoningToolsJSON | 28.3 | — | — | $0.255 | 205K |
| minimax-m2-her | — | — | — | $0.300 | 66K |
| minimax-m1 ReasoningTools | — | — | — | $0.550 | 1M |
| minimax-01 Vision | — | — | — | $0.200 | 1.0M |