mistral-medium-3-5Mistral AI
- endpoints
- 1
- regions
- 1
- api
- chat
- released
- April 2026
- eu routing
- available
capabilities 4/8
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  Mistral AI SAS | EU | 262K | $1.65 | $8.25 | $1.65 | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| τ²-Bench | 94.2 | |
| GPQA Diamond | 74.8 | |
| Coding Index | 46.9 | |
| SciCode | 40.2 | |
| Terminal-Bench Hard | 33.3 | |
| Intelligence Index | 14.9 | |
| Humanity's Last Exam | 13.8 | |
| 7 evals | mean | 45.4 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-04-29.
mistral-medium-3-5requesty routes this id across every provider serving mistral-medium-3-5, picking on price and health and failing over automatically. the id stays valid when a provider changes underneath it
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="mistral-medium-3-5", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
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.
questions 6
Which providers serve mistral-medium-3-5?
How much does mistral-medium-3-5 cost?
Is mistral-medium-3-5 open weights?
What is the context window of mistral-medium-3-5?
How do I use mistral-medium-3-5 with the OpenAI SDK?
Should I call mistral-medium-3-5 by its managed id or a provider id?
more from mistral ai 6
| model | context | from /M | providers |
|---|---|---|---|
| leanstral-1-5 | 262K | free | 1 |
| devstral-latest | 256K | $0.44 | 1 |
| mistral-medium-latest | 131K | $0.44 | 1 |
| mistral-small-2603 | 256K | $0.17 | 1 |
| mistral-large-latest | 131K | $0.55 | 1 |
| codestral-latest | 131K | $0.33 | 1 |
route mistral-medium-3-5 through one endpoint
One key for 1 provider on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology