Prior MiniMax coding model for agent workflows, office edits, and automationMiniMax-M2.5 is offered by 49 providers on this page. Public prices are shown for 40 of them. Its official list price is $0.30 per 1M input tokens and $1.20 per 1M output tokens. The lowest paid channel is DInference at $0.22 / $0.88 per 1M, about 1.4× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel and 8 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Median output speed is 53 tokens per second, with 1.8s to the first token.
The context window is 204,800 tokens at the reference host, but hosts report different limits, from 65,536 to 1,000,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| SCNet Token Plan MiniMax-M2.5 | Gateway | Subscription | $0 | — | 204,800 | 131,072 | ||
| Alibaba Token Plan (China) MiniMax-M2.5 | Gateway | Subscription | $0 | $0 | 196,608 ⚠ | 32,768 | ||
| Tencent Coding Plan (China) | Gateway | Subscription | $0 | $0 | 204,800 | 32,768 | deprecated | |
| OpenCode minimax-m2.5-free | Gateway | Free | $0 | — | 204,800 | 131,072 | deprecated | |
| Alibaba Token Plan MiniMax-M2.5 | Gateway | Subscription | $0 | $0 | 196,608 ⚠ | 32,768 | ||
| MiniMax Token Plan (minimax.cn) MiniMax-M2.5 | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | deprecated | |
| Alibaba Coding Plan MiniMax-M2.5 | Gateway | Subscription | $0 | $0 | 196,608 ⚠ | 24,576 | ||
| MiniMax Token Plan (minimax.io) MiniMax-M2.5 | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | deprecated | |
| Alibaba Coding Plan (China) MiniMax-M2.5 | Gateway | Subscription | $0 | $0 | 196,608 ⚠ | 24,576 | ||
| DInference | Gateway | $0.22 | $0.88 | — | — | 200,000 ⚠ | 32,000 | deprecated |
| MiniMax (minimax.io)Official MiniMax-M2.5 | First-party | $0.30 | $1.20 | $0.03 | $0.38 | 204,800 | 131,072 | deprecated |
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.
Interleaved thinking (reasoning between tool calls) is declared by 17 of 49 providers.
38 / 49 providers expose no reasoning control (reasoning_options: []).
9 more channels offer $0 (SCNet Token Plan, Alibaba Token Plan (China), Tencent Coding Plan (China) etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 75.8 | resolved | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Mini-SWE-Agent | 10.3 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Mini-SWE-Agent | 19.52 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Mini-SWE-Agent | 18.6 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.