Leanstral 1.5
Mistral AI released an updated model that helps mathematicians and programmers write and check formal proofs, available to developers through Mistral's service.
This came out before trckr began following Mistral API, so it was added on Nov 8 without an alert. Its release date comes from Mistral changelog.
Key facts
- Released
- Jun 30, 2026
- What it does
- Text and chat: Writes, answers questions and holds a conversation.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.Sees images: Understands pictures, screenshots and charts you share with it.
Can I use it?
In an app
No app mentioned so far.
For developers
Developers can use it now through an API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet..
Download
Not downloadable: it runs on the maker's own servers.
Price and limits
What developers pay to use it through the API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet., per million Tokens: The small chunks of text a model reads and writes, about three-quarters of a word each. Prices and limits are counted in tokens. sent (input) or written back (output), and how much it can take in at once.
- Input
- Free
- per million tokens
- Output
- Free
- per million tokens
- Context window: How much a model can keep in mind at once: your question, any files you share and its own replies. Measured in tokens; 1,000 tokens is about 750 words.
- 262K tokens
- about 200,000 words
View moreView less
- Longest answer
- 128K tokens (about 96,000 words)
From the lab's own listing on models.dev, checked .
Compare Leanstral 1.5 with
It came out 62 days after Mistral Medium 3.5, the lab's previous model.
The details
Mistral's updated Leanstral 1.5 is a specialised model for writing and checking Lean 4 formal proofs, with improved training data and longer Reasoning model: A model that thinks step by step before answering. Slower, but much better at maths, code and tricky questions.. It is available through Mistral's API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet..
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
labs-leanstral-1-5labs-leanstral-1-5-1Timeline
/Mistral APIOfficialFirst signal
labs-leanstral-1-5
/Mistral APIOfficial
labs-leanstral-1-5-1
Get alerts like this the moment they happen.
From Mistral AI and every other major lab.