MiniMax-M2.5-highspeedDeprecatedOpen weights
MiniMax · released 2026-02-13
The official API price of MiniMax-M2.5-highspeed is $0.6 per 1M input tokens and $2.4 per 1M output tokens (as of 2026-11-12). Context window: 205K tokens, up to 131K output tokens per request. 9 providers sell it. The lowest is Ofox: $0.3 input, $2.4 output. This model is marked as deprecated.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| MiniMax (minimax.io)OfficialDeprecatedMiniMax-M2.5-highspeed | $0.6 | $2.4 | $0.03 | OfficialDeprecated | Official docs |
OOfoxLowestminimax/ | $0.3 | $2.4 | $0.03 | Lowest | Official docs |
 DevPass (LLM Gateway)minimax-m2.5-highspeed | $0.6 | $2.4 | $0.03 | Official docs | |
LLLM Gatewayminimax/ | $0.6 | $2.4 | $0.03 | Official docs | |
MMerge Gatewayminimax/ | $0.6 | $2.4 | $0.03 | Official docs | |
OOrcaRouterminimax/ | $0.6 | $2.4 | $0.03 | Official docs | |
 Vercel AI Gatewayminimax/ | $0.6 | $2.4 | $0.03 | Official docs | |
 ZenMuxminimax/ | $0.6 | $2.4 | $0.03 | Official docs | |
QQiniuDeprecatedminimax/ | $0.608696 | $2.434783 | — | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
High-speed MiniMax model for low-latency coding and agent workflows
Description from models.dev.
Specs
- Type
- Text
- Context
- 205K
- Max output
- 131K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- No
- Knowledge cutoff
- 2025-01-01
- Open weights
- Yes
- Released
- 2026-02-13
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.