MiniMax M3.1 Flash
MiniMaxProprietary1M context
MiniMax M3.1 Flash is a proprietary model from MiniMax with a 1M-token context window. 6 providers list it, all at $0.15 per million input tokens and $0.60 per million output tokens.
- Maker
- MiniMax
- Licence
- Proprietary
- Context window
- 1M
- Providers listed
- 6
- Lowest input, per 1M
- $0.15
- Lowest output, per 1M
- $0.60
- MiniMax's own API, per 1M
- $0.15 in · $0.60 out
- Effort settings
- Max
Providers serving MiniMax M3.1 Flash
Cheapest first, by the blended rate of three input tokens to one output token. Prices in US dollars per million tokens, as of 26 Oct 2026.
| Provider | Input | Output | Context | Tools | JSON mode | OpenAI-compatible | Model ID |
|---|---|---|---|---|---|---|---|
DigitalOcean | $0.15 | $0.60 | 1.05M | Yes | — | Yes | minimax-m3.1-flash |
Fireworks | $0.15 | $0.60 | 1M | Yes | Yes | Yes | accounts/fireworks/models/minimax-m3p1-flash |
MiniMax | $0.15 | $0.60 | 1M | Yes | No | No | MiniMax-M3.1-Flash |
Nebius | $0.15 | $0.60 | 1.05M | Yes | Yes | Yes | MiniMaxAI/MiniMax-M3.1-Flash |
Novita | $0.15 | $0.60 | 1M | Yes | Yes | Yes | minimax/minimax-m3.1-flash |
Together AI | $0.15 | $0.60 | 1.05M | — | — | — | MiniMax-M3.1-Flash |
Benchmark scores
Published scores only, each linked to its source. Compare every model in Bench rankings
| Benchmark | Max |
|---|---|
APEX-Agents Agentic office work | 53.9% |