MiniMax (minimax.io): MiniMax-M2

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Model lab: MiniMax (minimax.io)
Model family: minimax

Model resources

Hugging Face

Modalitiestext → text

Context window204,800

Maximum output131,072

InputUSD 0.204 / 1M tokens

OutputUSD 0.816 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/minimax/m2.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/minimax/m2"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

MiniMax-M2 API Pricing

Type	Price information
Input	USD 0.204 / 1M tokens
Output	USD 0.816 / 1M tokens

Benchmarks

Intelligence Index · v4.318.6

Coding Index—

Agentic Index—

Benchmark	Score	Measurement	Source
SWE-Bench Verified	69.4	resolved

Performance

Output speed69.56 tokens/s

Time to first token1.4 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput69.56 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.3 sCurrent

Throughput

Current69.56 tok/s

Window average68.0 tok/s

Time to first token

Current1.4 s

Window average1.5 s

End-to-end latency

Current7.3 s

Window average7.5 s

Tail latency (P99)

Current17.4 s

Window average16.5 s

Prompt cache hit rate

Current18.5%

Window average24.6%

Error rate

Current0.0%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

MiniMax-M2 Compare models

Model	Input price	Output price	Context window	Capabilities
MiniMax-M2This page	USD 0.204 / 1M tokens	USD 0.816 / 1M tokens	204,800	Text output · Reasoning · Tool calling
MiniMax-M2.7	USD 0.064 / 1M tokens	USD 0.256 / 1M tokens	204,800	Text output · Reasoning · Tool calling
MiniMax-M2.7-highspeed	USD 0.48 / 1M tokens	USD 1.92 / 1M tokens	204,800	Text output · Reasoning · Tool calling
MiniMax-M2.5-highspeed	USD 0.24 / 1M tokens	USD 1.92 / 1M tokens	204,800	Text output · Reasoning · Tool calling
MiniMax-M2.5	USD 0.15504 / 1M tokens	USD 0.9032 / 1M tokens	204,800	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 204,800
Maximum output: 131,072
Release date: 2025-10-27
Attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is MiniMax-M2 for?

Efficient open MiniMax model built for coding agents and tool-heavy workflows

What inputs and outputs does MiniMax-M2 support?

Recorded inputs: text; outputs: text.

How is MiniMax-M2 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.204 / 1M tokens; Output USD 0.816 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for MiniMax-M2?

Current model records list Context window 204,800 tokens; Maximum output 131,072 tokens.

What model parameter does the Quickstart use?

The example uses moduck/minimax/m2. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.