MiniMax M2.5
Where it stands
Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.
About this model
MiniMax M2.5 is an AI model from MiniMax, made available through the API on February 12, 2026. It can read up to 204,800 tokens in one request, roughly 384 pages of text, and write up to 128,000 tokens in a single answer.
Through the API it costs $0.27 per million input tokens and $1.08 per million output tokens. Its pricing sits in the middle of the market.
It supports extended reasoning: it can "think" step by step before answering, which helps on maths, code and complex questions. It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (MiniMaxAI/MiniMax-M2.5), so it can also be downloaded and run on your own hardware.
Quality scores
Rankings →Where to use it
Companies that serve this model through an API: 8. Prices per million tokens, cheapest first.
| Provider | Inputi | Outputi | Contexti | Uptime (24 h)i |
|---|---|---|---|---|
VeniceCheapest | $0.27 | $0.95 | 198K | 95.9% |
StreamLake | $0.27 | $1.08 | 200K | 99.7% |
AtlasCloudfp8 | $0.30 | $1.20 | 192K | 99.7% |
DigitalOcean | $0.30 | $1.20 | 64K | 99.9% |
Friendli | $0.30 | $1.20 | 192K | 100.0% |
Novitafp8 | $0.30 | $1.20 | 200K | 99.8% |
MinimaxOfficialfp8 | $0.30 | $1.20 | 200K | 99.9% |
MinimaxOfficialfp8 | $0.60 | $2.40 | 200K | 99.6% |
Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.
Use it in your code
Call MiniMax M2.5 through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "minimax/minimax-m2.5", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="minimax/minimax-m2.5",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "minimax/minimax-m2.5",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$0.459
- Summarise a 100-page document$0.015
- An app with 10,000 requests a day for a month$211
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
Qwen3.5-122B-A10BAlibaba Qwen | $0.26 | $2.08 | 256K | Compare with ⇄ |
Gemini 3.1 Flash LiteGoogle DeepMind | $0.25 | $1.50 | 1M | Compare with ⇄ |
Trinity Large ThinkingArcee AI | $0.25 | $0.80 | 256K | Compare with ⇄ |
Seed-2.0-LiteByteDance Seed | $0.25 | $2 | 256K | Compare with ⇄ |
Mercury 2Inception | $0.25 | $0.75 | 128K | Compare with ⇄ |
Command A+Cohere | $0.30 | $1.50 | 192K | Compare with ⇄ |
Frequently asked questions
- How much does MiniMax M2.5 cost?
- MiniMax M2.5 costs $0.27 per million input tokens and $1.08 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.459.
- What is the context window of MiniMax M2.5?
- MiniMax M2.5 can read up to 204,800 tokens in one request, about 384 pages of text. It can write up to 128,000 tokens in a single answer.
- Is MiniMax M2.5 open source?
- Yes. Its weights are published (MiniMaxAI/MiniMax-M2.5), so you can download it and run it on your own hardware, or use it through one of 8 API providers.
- Who makes MiniMax M2.5?
- MiniMax M2.5 is made by MiniMax. It became available through the API on February 12, 2026.
- How good is MiniMax M2.5?
- MiniMax M2.5 has an overall index of 146.7 in Epoch AI’s independent tests, ranking #61 of 136 models we track.
- Can MiniMax M2.5 read images?
- No. MiniMax M2.5 only accepts text as input.
- What are the alternatives to MiniMax M2.5?
- Models with a similar price from other companies include Qwen3.5-122B-A10B, Gemini 3.1 Flash Lite and Trinity Large Thinking. You can compare them side by side on this page.