MiniMax-M2.5
MiniMax-M2.5 is a reasoning model from MiniMax released on Jan 15, 2025. It reads text and writes text, with a 205K token context window and up to 131K tokens per reply.
Show moreShow less
It costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input bills at $0.03, 90% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
28 providers serve it, including Amazon Bedrock, Friendli and Novita AI. The lowest input price is $0.1938 per million tokens at GreenPT.
- Modalities
- In / out price
- $0.30 / $1.20 per 1M
- Context
- 205K
- Max output
- 131K
- Released
- Jan 15, 2025
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
MiniMax-M2.5 pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.30 / 1M tokens | |
|---|---|---|
| Output | $1.20 / 1M tokens | |
| Cached input (read) | $0.03 / 1M tokens | 90% off input |
| Cache write | $0.375 / 1M tokens |
MiniMax-M2.5 providers
28 providers serve it, including Amazon Bedrock, Friendli and Novita AI. The lowest input price is $0.1938 per million tokens at GreenPT. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| MiniMax (minimax.io) First party | $0.30 | $1.20 | $0.03 | 205K | 131K |
| Amazon Bedrock | $0.30 | $1.20 | – | 197K | 98K |
| Friendli | $0.30 | $1.20 | $0.06 | 197K | 131K |
| Novita AI | $0.30 | $1.20 | $0.03 | 205K | 131K |
| Vercel AI Gateway | $0.30 | $1.20 | $0.03 | 205K | 131K |
| GreenPT | $0.1938 | $1.13 | $0.0627 | 205K | 131K |
| DInference | $0.22 | $0.88 | – | 200K | 32K |
| Venice AI | $0.27 | $0.95 | $0.03 | 198K | 33K |
| 302.AI | $0.30 | $1.20 | – | 205K | 131K |
| Alibaba (China) | $0.30 | $1.20 | – | 205K | 131K |
| DevPass (LLM Gateway) | $0.30 | $1.20 | $0.03 | 229K | 131K |
| DigitalOcean | $0.30 | $1.20 | $0.06 | 66K | 66K |
Showing 12 of 28 providers: the lab first, then the major clouds, then the cheapest resellers.
What MiniMax-M2.5 costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call MiniMax-M2.5 through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to MiniMax-M2.5
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 29.2
Reads text, images and video. Tool calling, structured output, reasoning. Served by 43 providers.
by minimaxMay 31, 20261M context$0.30/M input tokens$1.20/M output tokens43 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 39 providers.
by openaiJul 9, 2026$0.20/M input tokens$1.20/M output tokens39 providers
- 524K context
Reads text. Tool calling, structured output, reasoning. Served by 5 providers.
by upstageAug 6, 2026$0.30/M input tokens$1.20/M output tokens5 providers
- 512K context
Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.
by minimaxMay 3, 2026$0.30/M input tokens$1.20/M output tokens2 providers
- 205K context
Reads text. Tool calling, structured output, reasoning. Served by 35 providers.
by minimaxMar 18, 2026$0.30/M input tokens$1.20/M output tokens35 providers
- 205K context
Reads text. Tool calling, structured output, reasoning. Served by 17 providers.
by minimaxDec 22, 2025$0.30/M input tokens$1.20/M output tokens17 providers
More from MiniMax
MiniMax H3 Max
VideoGenerates video from text and images.
by minimaxAug 27, 2026
MiniMax H3
VideoGenerates video from text and images.
by minimaxJul 31, 2026
- Index 29.2
Reads text, images and video. Tool calling, structured output, reasoning. Served by 43 providers.
by minimaxMay 31, 20261M context$0.30/M input tokens$1.20/M output tokens43 providers
- 512K context
Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.
by minimaxMay 3, 2026$0.30/M input tokens$1.20/M output tokens2 providers
- 205K context
Reads text. Tool calling, structured output, reasoning. Served by 35 providers.
by minimaxMar 18, 2026$0.30/M input tokens$1.20/M output tokens35 providers
- 205K context
Reads text. Tool calling, structured output, reasoning. Served by 16 providers.
by minimaxMar 18, 2026$0.60/M input tokens$2.40/M output tokens16 providers
MiniMax-M2.5 questions
How much does the MiniMax-M2.5 API cost?
$0.30 per million input tokens and $1.20 per million output tokens, with cached input at $0.03. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of MiniMax-M2.5?
204,800 tokens of input, and it can write up to 131,072 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve MiniMax-M2.5?
28 providers serve it, including Amazon Bedrock, Friendli and Novita AI. The lowest input price is $0.1938 per million tokens at GreenPT. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does MiniMax-M2.5 support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is MiniMax-M2.5 open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was MiniMax-M2.5 released?
Jan 15, 2025.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on MiniMax-M2.5?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting