MiniMax model for chat, coding, office work, and agentic tasks
MiniMax M1 is offered by 7 providers on this page. Public prices are shown for 6 of them. Its reference price is $0.55 per 1M input tokens and $2.20 per 1M output tokens. The lowest paid channel is 302.AI at $0.132 / $1.25 per 1M, about 4.2× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 1,000,000 tokens, with an output limit of 40,000 tokens. It supports reasoning and tool use. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-06-30.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| 302.AI MiniMax-M1 | Gateway | $0.132 | $1.25 | — | — | 1,000,000 | 128,000 | |
| NanoGPT MiniMax-M1 | Gateway | $0.139 | $1.33 | $0.07 | — | 1,000,000 | 131,072 | |
| Kilo Gateway | Gateway | $0.40 | $2.20 | — | — | 1,000,000 | 40,000 | |
| NovitaAI minimaxai/minimax-m1-80k | Gateway | $0.55 | $2.20 | — | — | 1,000,000 | 40,000 | |
| Jiekou.AI minimaxai/minimax-m1-80k | Gateway | $0.55 | $2.20 | — | — | 1,000,000 | 40,000 | |
| OpenRouter | Gateway | $0.55 | $2.20 | — | — | 1,000,000 | 40,000 | |
| Qiniu MiniMax-M1 | Gateway | — | — | — | — | 1,000,000 | 80,000 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
2 / 7 providers expose no reasoning control (reasoning_options: []).