ModelMistral AI · Joined Apr 28, 2026

Mistral Medium 3.5

Model at Mistral AI

Mistral Medium 3.5 does not have a researched profile yet. Everything here comes from its recorded changes and public listings, each linked to its source.

The basics

As of Nov 1
Status
Available
Price
$1.50 in, $7.50 outPer 1M tokens, since Apr 28
Context
262K tokens
Open weights
Yes

About me

The model wrote this when we asked it to describe itself. We have not edited or checked it.

I’m highly organized and proactive, which helps keep projects on track. I sometimes get deeply focused on details, which can slow me down when quick decisions are needed. A colleague can work well with me by giving clear priorities and deadlines upfront.

How this was written

mistralai/mistral-medium-3-5 wrote this through its own API on Oct 25, 2026, from this prompt: "Write exactly three first-person sentences about what you are like to work with. Describe one strength, one limitation, and how a colleague can work well with you. Do not invent measurements or claim independent verification."

Updates

Where it works

PlacePrice per 1M tokens, in / outUptime
Mistral$1.50 / $7.5099.91%

Prices and uptime are OpenRouter's figures for each provider's cheapest endpoint. Uptime covers the last 24 hours.

Benchmarks

Higher is better. Green is Mistral Medium 3.5. Dark marks are similar models.

Independent

What people say

Reviews

No reviews yet. Be the first to review Mistral Medium 3.5.

Used Mistral Medium 3.5? Tell other builders what worked and what did not.

Writing habits

dashes used like commas, per 1,000 words
8.92
uses of "delve"
None in 36 replies
words from our AI cliché list, per 1,000 words
0.2
"not X but Y" phrases per 1,000 words
0.14
replies with headings or bullet lists
25 of 36
typical reply length in words
411 words
says only "OK" when told to
Yes
How we measured this

12 fixed everyday prompts, 3 replies each, default API settings, prose only (code removed). Method version 3. Dashes count em dashes, spaced en dashes and double hyphens, not hyphens inside words. Measured Oct 25, 2026.