NOUMENOpen app
NOUMEN

MiniMax · Open weights

MiniMax M2.1

Added Jan 20, 2025Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

MiniMax M2.1 builds on M2 with enhanced context understanding and improved complex tool use. 230B parameter MoE model (10B active) optimized for agentic workflows and long-horizon tasks.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.30
Output
$1.20
Cache read
$0.03

Reference prices as published by the model provider. API example

Specifications

Context window
200K
Max output
131.1K
Average output (7 days)
359 tokens
Longer than 37% of 465 models

Side by side

MiniMax M2.1 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

MiniMax M2.1MiniMaxThis modelGPT 5.1 Codex MiniOpenAIRemove
ProviderMiniMaxOpenAI
Discovery tierOpen weightsEfficient
AddedJan 20, 2025Nov 13, 2025
Limits
Context window200K400KBest
Max output131.07KBest128K
Average output359 tokens136 tokens
Pricing, USD per 1M tokens
Input$0.30$0.25Best
Output$1.20Best$2.00
Cache read$0.03$0.025Best
Benchmark indexes
Intelligence Index20.9Best20.4
Math Index82.791.7Best
Capabilities
ReasoningYesYes
ToolsYesNo
VisionNoYes
Structured outputYesNo
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • MiniMax M2.1
  • GPT 5.1 Codex Mini

Intelligence Index

  • MiniMax M2.120.9
  • GPT 5.1 Codex Mini20.4

MiniMax M2.1: Better than 51% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • MiniMax M2.1: 82.7
    • GPT 5.1 Codex Mini: 91.7Top

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • MiniMax M2.1: 67.7%Top
    • GPT 5.1 Codex Mini: 66.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • MiniMax M2.1: 23.2%Top
    • GPT 5.1 Codex Mini: 18.5%

  • GPQA Diamond

    Graduate-level science questions

    • MiniMax M2.1: 83.0%Top
    • GPT 5.1 Codex Mini: 81.3%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • MiniMax M2.1: 87.5%Top
    • GPT 5.1 Codex Mini: 82.0%

  • IFBench

    Following precise output instructions

    • MiniMax M2.1: 69.9%Top
    • GPT 5.1 Codex Mini: 67.9%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • MiniMax M2.1: 81.0%
    • GPT 5.1 Codex Mini: 83.6%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • MiniMax M2.1: 82.7%
    • GPT 5.1 Codex Mini: 91.7%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • MiniMax M2.1: 28.8%
    • GPT 5.1 Codex Mini: 33.3%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • MiniMax M2.1: 85.4%Top
    • GPT 5.1 Codex Mini: 62.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • MiniMax M2.1: 67.7%Top
    • GPT 5.1 Codex Mini: 66.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m2.1",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="minimax/minimax-m2.1",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

MiniMax

Other MiniMax models, starting with the same family.