MiniMax M2

minimax-m2 by Minimax Released October 24, 2025
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.3 / 1M
Output from
$1.2 / 1M
Cached input from
$ / 1M
Context window
1M
Endpoints
4
from 3 providers
Regions
Global, Asia, Europe, United States

About MiniMax M2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.

MiniMax M2 is a chat model by Minimax, available on Eden AI through 4 endpoints from 3 providers, from $0.3 per million input tokens and $1.2 per million output tokens, with a context window of up to 1M tokens.

Providers and prices

4 endpoints from 3 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Amazon Web Services (Europe)Official−%amazon/minimax.minimax-m2
Europe
1M
$0.3$0.3
$1.2
$
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (United States)Official−%amazon/minimax.minimax-m2@us
United States
1M
$0.3$0.3
$1.2
$
ReasoningToolsJSONCacheVisionWeb
Minimax (Asia)Official−%minimax/MiniMax-M2
Asia
205K
$0.3$0.3
$1.2
$
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/minimaxai/minimax-m2-maas
Global
197K
$0.3$0.3
$1.2
$
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
2.74 s
Minimax (Asia)
Lowest latency
4.52 s
Minimax (Asia)
Highest throughput
32.87 tok/s
Minimax (Asia)
Best availability
100%
Minimax (Asia)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Amazon Web Services (Europe)
s
s
s
tok/s
%
%
%
%
Amazon Web Services (United States)
s
s
s
tok/s
%
%
%
%
Minimax (Asia)
2.74 s
4.52 s
13.18 s
32.87 tok/s
100%
0%
0%
0%
Google Cloud
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call MiniMax M2 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about MiniMax M2

On Eden AI, prices for this model start at $0.3 per million input tokens and $1.2 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 1M tokens, depending on the endpoint.

4 endpoints from 3 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 2.74 s (Minimax (Asia)) and the highest throughput was 32.87 tokens per second (Minimax (Asia)).