Can I run MiniMax M2.7 locally?

Yes, the weights are open and available on Hugging Face. MiniMax recommends SGLang or vLLM for serving; given the model's scale, you will need substantial GPU memory.

What does MiniMax M2.7 cost via API?

MiniMax prices it at $0.30 per million input tokens and $1.20 per million output tokens, with a 204,800-token context window.

How does M2.7 differ from other coding-focused models?

Its distinguishing angle is self-evolution and native multi-agent orchestration: it can build and refine its own agent scaffolding autonomously, which goes beyond standard code generation into full engineering workflow management.

MiniMax M2.7

2002°

#llm #minimax #reasoning #coding #agents #long context

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

MiniMax | 204,800 token context | $0.30/M input, $1.20/M output. MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.

Guides for this model

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

Open weights vs open source vs API-only: what you are actually allowed to do

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

MiniMax M2.7 is an open-weights large language model from MiniMax built around autonomous, multi-agent work: software engineering, live debugging, financial modeling, and document production. Its headline trait is self-evolution — an internal version improved its own programming scaffold 30% over 100+ rounds without human intervention. It suits teams running production engineering workflows who want a capable, self-hostable model at a modest API price.

Known for

SWE-Pro score of 56.2%, matching top closed-source coding rivals
Multi-agent collaboration with stable role identity across complex task pipelines
Self-evolution: autonomously rewrites and evaluates its own scaffolding
High-fidelity editing of Word, Excel and PowerPoint files as editable deliverables
204,800-token context window with open weights available on Hugging Face

Watch out for

This is a large model; local deployment demands serious hardware — check VRAM requirements before downloading
Open weights come with a licence file; read it before any commercial or derivative use
Self-evolution and agent-team features shine in orchestrated pipelines, not casual single-turn chat

Best for

Prompts to try

Production incident triage

You are an SRE. Here is a stack trace and the last 50 lines of application logs from a Node.js service that started returning 500s at 14:32 UTC. Identify the root cause, list the three most likely contributing factors in order of probability, and write the one-line fix you would apply first. Paste your logs below.

Multi-step financial model

Build a three-statement financial model for a SaaS business with 500 customers paying $200/month, 5% monthly churn, $50 CAC, and $30 monthly COGS per customer. Project 12 months of income statement, cash flow, and ending cash balance. Show your formulas and flag the month the business turns cash-flow positive.

Agent task decomposition

You are coordinating a team of specialist agents: a web-search agent, a code-execution agent, and a document-writing agent. A user wants a competitive analysis of three open-source vector databases — Qdrant, Weaviate, and Milvus — delivered as a structured report. Write the full task plan: which agent handles which step, in what order, and what each agent's output must contain before the next step begins.

Compare with

MiniMax M1
API-only model
1,000,000 token context · $0.55/M input, $2.20/M output
MiniMax M3
Open-weights model
1,048,576 token context · $0.30/M input, $1.20/M output
MiniMax M2.5
Open-weights model
204,800 token context · $0.27/M input, $0.95/M output
MiniMax M2.1
Open-weights model
204,800 token context · $0.30/M input, $1.20/M output

More text models from minimax

Questions people ask

Can I run MiniMax M2.7 locally?: Yes, the weights are open and available on Hugging Face. MiniMax recommends SGLang or vLLM for serving; given the model's scale, you will need substantial GPU memory.
What does MiniMax M2.7 cost via API?: MiniMax prices it at $0.30 per million input tokens and $1.20 per million output tokens, with a 204,800-token context window.
How does M2.7 differ from other coding-focused models?: Its distinguishing angle is self-evolution and native multi-agent orchestration: it can build and refine its own agent scaffolding autonomously, which goes beyond standard code generation into full engineering workflow management.

Captain's verdict
A serious open-weights engineering model — the self-evolution story is real, not marketing, and the agentic depth is rare at this price.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Qwen3 VL 32B Instruct

TEXT / LLM

AI Models for Image, Video & Text Generation

MiniMax M2.7 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm minimax reasoning coding agents long context local

Browse by Model Family