MI
Compareminimax/minimax-m3.1-flash
MiniMax multimodal model for agentic reasoning, tool use, coding and long-context tasks. It accepts text, images and video, generates text, supports adjustable reasoning effort and has a one-million-token context window. Official weights are announced for a later release.
- Context window
- 1M
- Input
- Image · Text · Video
- Output
- Text
- Released
- 2026-10-19
- Capabilities
- Reasoning, Tool call
IN
$0.15
USD / 1,000,000 token
MiniMax global API; pay-as-you-go; standard
OUT
$0.60
USD / 1,000,000 token
MiniMax global API; includes thinking tokens
Cache read
$0.015
USD / 1,000,000 token
MiniMax global API; cached input tokens
Performance
Overall capability
55.1/100
- Coding
- 55.1
- Reasoning
- 61.4
- Professional work
- 56.7
- Knowledge & language
- 52.5
| Terminal-Bench 4.0 (AA rerun)MiniMax-M3.1-Flash | Coding | Artificial Analysis | 2026-11-05 | |
| Harvey Legal Agent Benchmark | Professional work | Vals AI / Harvey | 2026-11-05 | |
| CritPtMiniMax-M3.1-Flash | Reasoning | Artificial Analysis | 2026-11-05 | |
| GDPval-AA | Professional work | Artificial Analysis | 2026-11-05 | |
| Humanity’s Last ExamMiniMax-M3.1-Flash | Reasoning | Artificial Analysis | 2026-11-05 | |
| τ³-Banking | Professional work | Mercor | 2026-11-05 | |
| APEX-Agents 1.1 | Professional work | Mercor | 2026-11-05 | |
| Terminal-Bench 4.0 (Vals rerun) | Coding | Vals AI | 2026-11-05 |
Providers
| Input | Output | Cache read | Cache write | ||||
|---|---|---|---|---|---|---|---|
| MiniMax (minimax.io) | MiniMax-M3.1-Flash | Openai chat | - | - | - | - | - |
ModelRegistry · Catalog updated 2026-11-05