High-speed MiniMax model for low-latency coding and agent workflows
MiniMax-M2.5-highspeed is offered by 12 providers on this page. Public prices are shown for 9 of them. Its official list price is $0.60 per 1M input tokens and $2.40 per 1M output tokens. It also has 2 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 204,800 tokens, with an output limit of 131,072 tokens. 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 2025-01-01.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| MiniMax Token Plan (minimax.io) MiniMax-M2.5-highspeed | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | ||
| MiniMax Token Plan (minimax.cn) MiniMax-M2.5-highspeed | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | ||
| NovitaAI | Gateway | $0.60 | $2.40 | $0.03 | — | 204,800 | 131,072 | |
| MiniMax (minimax.cn)Official MiniMax-M2.5-highspeed | First-party | $0.60 | $2.40 | $0.06 | $0.38 | 204,800 | 131,072 | |
| Vercel AI Gateway | Cloud | $0.60 | $2.40 | $0.03 | $0.38 | 204,800 | 131,000 | |
| OrcaRouter | Gateway | $0.60 | $2.40 | $0.03 | $0.38 | 204,800 | 131,072 | |
| Merge Gateway | Gateway | $0.60 | $2.40 | $0.06 | $0.38 | 204,800 | 8,192 | |
| MiniMax (minimax.io)Official MiniMax-M2.5-highspeed | First-party | $0.60 | $2.40 | $0.06 | $0.38 | 204,800 | 131,072 | |
| DevPass (LLM Gateway) | Gateway | $0.60 | $2.40 | $0.03 | $0.38 | 204,800 | 131,072 | |
| LLM Gateway | Gateway | $0.60 | $2.40 | $0.03 | — | 204,800 | 131,100 | |
| ZenMux minimax/minimax-m2.5-lightning | Gateway | $0.60 | $4.80 | $0.06 | $0.75 | 204,800 | 131,072 | |
| Qiniu | Gateway | — | — | — | — | 204,800 | 128,000 | 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.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 12 providers.
8 / 12 providers expose no reasoning control (reasoning_options: []).
2 more channels offer $0 (MiniMax Token Plan (minimax.io), MiniMax Token Plan (minimax.cn)); free tiers usually have rate limits and no SLA, excluded from ranking.