Can I run Mistral Medium 3.5 locally?

Mistral AI describes it as open weights and self-hostable on as few as four GPUs, but no Hugging Face repository is currently listed, so check Mistral's own channels for the actual download.

What does Mistral Medium 3.5 cost and what is the context window?

It is priced at $1.50 per million input tokens and $7.50 per million output tokens, with a 262,144-token (256K) context window.

How does Mistral Medium 3.5 differ from other Mistral models?

It adds native vision input, a configurable per-request reasoning effort setting, and a focus on multi-tool agentic workflows that smaller Mistral models do not offer at the same scale.

Mistral Medium 3.5

3081°

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

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 | 262,144 token context | $1.50/M input, $7.50/M output. Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.

Guides for this model

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

How much VRAM do I actually need for local AI?

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

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Mistral Medium 3.5 is a 128B dense model from Mistral AI with a 256K context window, vision input, and configurable reasoning effort per request. It targets agentic workflows and multi-step tasks, with particular strength in reliable multi-tool calling. Open weights and self-hostable on four GPUs, it sits in a useful middle ground between lightweight and frontier-scale models.

Known for

Reliable multi-tool calling across long-horizon agentic tasks
Configurable reasoning effort adjustable per individual request
Vision encoder handles variable image sizes and aspect ratios natively
256K context window for large documents or extended conversations
Self-hostable on as few as four GPUs despite 128B parameter count

Watch out for

Open weights are claimed but no Hugging Face repository is currently listed; verify availability before building on it.
At $7.50/M output tokens, costs climb fast on agentic loops that generate long responses.
128B means serious hardware requirements for self-hosting; four GPUs is the floor, not a casual setup.

Best for

Prompts to try

Multi-tool agent plan

You have access to a web search tool, a code execution tool, and a file-read tool. A user wants to know the current exchange rate between EUR and JPY, then calculate how much 4,750 EUR is worth in JPY, and save the result to a file called result.txt. Write the full tool-calling sequence you would execute, step by step, with the exact arguments you would pass to each tool.

Reason through a tricky bug

This Python function is supposed to return the second-largest unique number in a list, but it fails silently on some inputs. Identify every edge case that could cause wrong output or an exception, explain why each one breaks the function, then rewrite it to handle all of them: def second_largest(nums): nums = sorted(set(nums)) return nums[-2]

Analyse an image in detail

Attach a screenshot of a dashboard, chart, or diagram. Describe every data point or UI element you can see, identify any anomalies or trends, and suggest two concrete actions a product team could take based on what the image shows.

Compare with

Ministral 3 14B 2512
Open-weights model
262,144 token context · $0.20/M input, $0.20/M output
Mistral Small 4
Open-weights model
262,144 token context · $0.15/M input, $0.60/M output
Devstral 2 2512
Open-weights model
262,144 token context · $0.40/M input, $2.00/M output
Mistral Small 3.1 24B
Open-weights model
128,000 token context · $0.35/M input, $0.55/M output

More text models from mistralai

Questions people ask

Can I run Mistral Medium 3.5 locally?: Mistral AI describes it as open weights and self-hostable on as few as four GPUs, but no Hugging Face repository is currently listed, so check Mistral's own channels for the actual download.
What does Mistral Medium 3.5 cost and what is the context window?: It is priced at $1.50 per million input tokens and $7.50 per million output tokens, with a 262,144-token (256K) context window.
How does Mistral Medium 3.5 differ from other Mistral models?: It adds native vision input, a configurable per-request reasoning effort setting, and a focus on multi-tool agentic workflows that smaller Mistral models do not offer at the same scale.

Captain's verdict
A serious agentic workhorse with vision and a long context; the output price means you will want to keep responses tight.

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

ERNIE 4.5 VL 424B A47B

TEXT / LLM

GPT Mini Latest

TEXT / LLM

AI Models for Image, Video & Text Generation

Mistral Medium 3.5 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 reasoning agents coding long context

Browse by Model Family