Can I run Mistral Medium 3.1 locally?

No. The weights are not publicly released, so you can only access it through Mistral's API or supported cloud deployments; there is nothing to download and run on your own hardware.

What does Mistral Medium 3.1 cost and how long is its context?

It is priced at $0.40 per million input tokens and $2.00 per million output tokens, with a 131,072-token context window.

How does Mistral Medium 3.1 differ from Mistral Large or Mistral Small?

Mistral positions Medium 3.1 as the cost-efficient middle ground: closer to frontier accuracy than Small, but significantly cheaper than Large-class models, with the added multimodal vision capability that earlier Medium versions lacked.

Mistral Medium 3.1

1946°

#llm #mistralai #vision #coding #reasoning #agents

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.

Mistral | 131,072 token context | $0.40/M input, $2.00/M output. Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid,…Mistral | 131,072 token context | $0.40/M input, $2.00/M output. Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.

Guides for this model

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

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

How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Mistral Medium 3.1 is Mistral AI's updated mid-tier model with vision support and a 131,072-token context window, priced well below the frontier heavyweights it competes with. It targets coding, STEM reasoning, and enterprise workflows where you need solid accuracy without paying large-model rates. If you are building something that needs to scale, the cost-to-capability ratio is the main reason to look here.

Known for

Strong coding and STEM reasoning at a fraction of large-model cost
Vision support alongside text, covering multimodal tasks
131k context window handles long documents and codebases
Supports on-prem and in-VPC deployment for sensitive enterprise use
Competitive with Claude Sonnet and Llama 4 Maverick class models

Watch out for

Weights are not public; you are renting access, not owning anything you can run locally.
Output tokens cost 5× more than input tokens, so verbose tasks add up quickly.
No model card details published, so independent capability verification is limited.

Best for

Prompts to try

Debug a tricky function

Here is a Python function that is supposed to parse nested JSON and return a flat dictionary with dot-notation keys, but it silently drops keys when a value is an empty list. Find the bug, explain why it happens, and give me a corrected version with a brief test case that would have caught it.

Analyse an attached diagram

I am attaching a system architecture diagram. Identify any single points of failure, note which services lack redundancy, and suggest the two highest-priority changes an engineering team should make before moving this to production.

STEM reasoning under constraints

A factory has three machines. Machine A produces 120 units per hour with a 2% defect rate. Machine B produces 95 units per hour with a 1% defect rate. Machine C produces 150 units per hour with a 4% defect rate. If the factory needs at least 300 good units per hour and wants to minimise total defects, which machines should run and at what allocation? Show your reasoning.

Compare with

Mistral Small 4
Open-weights model
262,144 token context · $0.15/M input, $0.60/M output
Mistral Small 3.2 24B
Open-weights model
256,000 token context · $0.09/M input, $0.25/M output
Mistral Large 4
API-only model
1,048,576 token context · $0.68/M input, $2.09/M output
Mistral Small 3.2 24B Instruct 2506
Open-weights model
128,000 token context · $0.07/M input, $0.20/M output

More text models from mistralai

Questions people ask

Can I run Mistral Medium 3.1 locally?: No. The weights are not publicly released, so you can only access it through Mistral's API or supported cloud deployments; there is nothing to download and run on your own hardware.
What does Mistral Medium 3.1 cost and how long is its context?: It is priced at $0.40 per million input tokens and $2.00 per million output tokens, with a 131,072-token context window.
How does Mistral Medium 3.1 differ from Mistral Large or Mistral Small?: Mistral positions Medium 3.1 as the cost-efficient middle ground: closer to frontier accuracy than Small, but significantly cheaper than Large-class models, with the added multimodal vision capability that earlier Medium versions lacked.

Captain's verdict
A sensible choice when you need near-frontier coding and reasoning at scale and the bill for a larger model is genuinely hard to justify.

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

Claude Opus 5

TEXT / LLM

Qwen3 30B A3B Thinking 2507

TEXT / LLM

Qwen2.5 72B Instruct

TEXT / LLM

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

TEXT / LLM

AI Models for Image, Video & Text Generation

Mistral Medium 3.1 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 mistralai vision coding reasoning agents

Browse by Model Family