NOUMENOpen app
NOUMEN

MiniMax · Open weights

MiniMax M2.7 Turbo

Added Mar 18, 2026Open weights

Compare models

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

Loading models…

Use in the app

MiniMax M2.7 Turbo is the highspeed and higher priced route for M2.7.

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

Pricing

USD per 1M tokens
Input
$0.60
Output
$2.40
Cache read
$0.06

Reference prices as published by the model provider. API example

Specifications

Context window
204.8K
Max output
131.1K
Average output (7 days)
644 tokens
Longer than 58% of 468 models

Side by side

MiniMax M2.7 Turbo 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 M2.7 TurboMiniMaxThis modelMiniMax M3.1 FlashMiniMaxRemove
ProviderMiniMaxMiniMax
Discovery tierOpen weightsEfficient
AddedMar 18, 2026Oct 19, 2026
Limits
Context window204.8K1.05MBest
Max output131.07K524.29KBest
Average output644 tokens1.4K tokens
Pricing, USD per 1M tokens
Input$0.60$0.15Best
Output$2.40$0.60Best
Cache read$0.06$0.015Best
Performance
Throughput—119.8 tok/s
Time to first token—7.0 s
Request success (24h)—99.7%
Benchmark indexes
Intelligence Index22.842.7Best
Coding Index52.6—
Capabilities
ReasoningYesYes
ToolsYesYes
VisionNoYes
Structured outputYesNo
Video inputNoYes
Reasoning effort—low, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • MiniMax M2.7 Turbo
  • MiniMax M3.1 Flash

Intelligence Index

  • MiniMax M2.7 Turbo22.8
  • MiniMax M3.1 Flash42.7

MiniMax M2.7 Turbo: Better than 55% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • MiniMax M2.7 Turbo: 52.6
    • MiniMax M3.1 Flash: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • MiniMax M2.7 Turbo: 4.4%
    • MiniMax M3.1 Flash: 72.5%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • MiniMax M2.7 Turbo: 0.3%
    • MiniMax M3.1 Flash: 38.1%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • MiniMax M2.7 Turbo: 718 Elo
    • MiniMax M3.1 Flash: 1,473 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • MiniMax M2.7 Turbo: 1,008 Elo
    • MiniMax M3.1 Flash: 1,458 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • MiniMax M2.7 Turbo: 6.0%
    • MiniMax M3.1 Flash: 20.8%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • MiniMax M2.7 Turbo: 78.3%
    • MiniMax M3.1 Flash: 79.7%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • MiniMax M2.7 Turbo: 5.6%
    • MiniMax M3.1 Flash: 16.7%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • MiniMax M2.7 Turbo: 29.6%
    • MiniMax M3.1 Flash: 48.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • MiniMax M2.7 Turbo: 87.4%
    • MiniMax M3.1 Flash: —

  • IFBench

    Following precise output instructions

    • MiniMax M2.7 Turbo: 75.7%
    • MiniMax M3.1 Flash: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • MiniMax M2.7 Turbo: 0.0%
    • MiniMax M3.1 Flash: 25.8%Top

  • SciCode

    Scientific computing in Python

    • MiniMax M2.7 Turbo: 50.1%
    • MiniMax M3.1 Flash: 53.4%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • MiniMax M2.7 Turbo: 39.4%
    • MiniMax M3.1 Flash: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • MiniMax M2.7 Turbo: 84.8%
    • MiniMax M3.1 Flash: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • MiniMax M2.7 Turbo: 78.3%
    • MiniMax M3.1 Flash: 79.7%Top

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-m2.7-turbo",
    "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-m2.7-turbo",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

MiniMax

Other MiniMax models, starting with the same family.