MiniMax M3.1 Flash
by Refuseless · family minimax · listed Oct 2026RTW
Frontier multimodal coding model with 1M context window and tunable thinking depth
Current rates USD per 1M tokens
Input$0.02
Output$0.08
Cache read$0.002
Cache write—
Against the market
On the record
- Model id
minimax-m3.1-flash- Context window
- 1.0M tokens
- Max output
- 512K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-10-19
- Last updated
- 2026-10-19
- Provider docs
- docs.refuseless.com/models
Back of the envelope
≈
Also listed at
- MiniMax Token Plan (minimax.io)free in · free out
- MiniMax Token Plan (minimax.cn)free in · free out
- Nvidiafree in · free out
- Tenstorrent$0.05 in · $0.20 out
- Eden AI$0.075 in · $0.30 out
- OpenRouter$0.075 in · $0.30 out
- Kilo Gateway$0.075 in · $0.30 out
- Obscurify.ai$0.0975 in · $0.39 out
- DevPass (LLM Gateway)$0.10 in · $0.50 out
- LLM Gateway$0.10 in · $0.50 out
- MiniMax (minimax.cn)$0.149 in · $0.598 out
- Merge Gateway$0.15 in · $0.60 out
- Nebius Token Factory$0.15 in · $0.60 out
- OpenCode Go$0.15 in · $0.60 out
- ClinePass$0.15 in · $0.60 out