NOUMENOpen app
NOUMEN

MiniMax · Balanced

MiniMax M1 80K

Added Jan 8, 2025

Compare models

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

Loading models…

Use in the app

MiniMax-M1 with 80K thinking budget. Enhanced version of the hybrid MoE reasoning model with double the thinking capacity. Ideal for extremely complex software engineering, tool use, and long context tasks.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$0.61
Output
$2.42

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
131.1K

Side by side

MiniMax M1 80K 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 M1 80KMiniMaxThis modelQwen 3 Coder 480BQwenRemove
ProviderMiniMaxQwen
Discovery tierBalancedOpen weights
AddedJan 8, 2025Mar 17, 2026
Limits
Context window1MBest262K
Max output131.07KBest65.54K
Average output—315 tokens
Pricing, USD per 1M tokens
Input$0.61$0.13Best
Output$2.42$0.50Best
Performance
Throughput—212.9 tok/s
Time to first token—12.3 s
Request success (24h)—95.4%
Benchmark indexes
Intelligence Index11.711.9Best
Math Index61.0Best39.3
Capabilities
ToolsNoYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • MiniMax M1 80K
  • Qwen 3 Coder 480B

Intelligence Index

  • MiniMax M1 80K11.7
  • Qwen 3 Coder 480B11.9

MiniMax M1 80K: Better than 26% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • MiniMax M1 80K: 61.0Top
    • Qwen 3 Coder 480B: 39.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • MiniMax M1 80K: 57.7%Top
    • Qwen 3 Coder 480B: 45.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • MiniMax M1 80K: 8.9%Top
    • Qwen 3 Coder 480B: 4.5%

  • GPQA Diamond

    Graduate-level science questions

    • MiniMax M1 80K: 69.7%Top
    • Qwen 3 Coder 480B: 61.8%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • MiniMax M1 80K: 81.6%Top
    • Qwen 3 Coder 480B: 78.8%

  • IFBench

    Following precise output instructions

    • MiniMax M1 80K: 41.8%Top
    • Qwen 3 Coder 480B: 40.5%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • MiniMax M1 80K: 71.1%Top
    • Qwen 3 Coder 480B: 58.5%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • MiniMax M1 80K: 61.0%Top
    • Qwen 3 Coder 480B: 39.3%

  • AIME

    Competition mathematics

    • MiniMax M1 80K: 84.7%Top
    • Qwen 3 Coder 480B: 47.7%

  • MATH-500

    Competition math problems

    • MiniMax M1 80K: 98.0%Top
    • Qwen 3 Coder 480B: 94.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • MiniMax M1 80K: 3.0%
    • Qwen 3 Coder 480B: 18.9%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • MiniMax M1 80K: 34.2%
    • Qwen 3 Coder 480B: 43.6%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • MiniMax M1 80K: 57.7%Top
    • Qwen 3 Coder 480B: 45.7%

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": "MiniMaxAI/MiniMax-M1-80k",
    "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="MiniMaxAI/MiniMax-M1-80k",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

MiniMax

Other MiniMax models, starting with the same family.