by MistralReleased 1 December 2025
Mistral Large 3 is a very large model you can download under an open Apache 2.0 licence and also run yourself. It takes text, pictures and files and answers in text, reading about 262 pages at once, and it can use tools and fill in exact forms you give it. Pick it for demanding general work where an open licence matters.
Reads about 260 pages · writes up to 200 pages
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_pstopseedfrequency_penaltypresence_penaltyStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceNo. Mistral has retired it. Other Mistral models are on sale.
Mistral Large 3 is a very large model you can download under an open Apache 2.0 licence and also run yourself. It takes text, pictures and files and answers in text, reading about 262 pages at once, and it can use tools and fill in exact forms you give it. Pick it for demanding general work where an open licence matters.
Mistral says it supports dozens of languages, naming French and Arabic among them. Darja is not named.
It reads text, images and PDFs. Up to 262K tokens in one request, about 260 pages. It writes up to 157 000 words at once.
Yes, its weights are public.
Mistral. Released 1 December 2025.
Mistral's flagship speech-to-text model that turns audio into transcripts with word timestamps and speaker labels, with context biasing for domain-specific vocabulary
The Voxtral Mini derivative that only transcribes, taking audio from meetings, voice notes and podcasts and returning the text through a standard transcription request
Mistral's compact speech-to-text model that turns audio into transcripts with word timestamps and speaker labels, and can be steered with context biasing to catch domain terms
Mistral AI's text embedding model from late 2023, whose 1024-dimension vectors capture how passages relate, for semantic search and RAG; Codestral Embed is the version for code
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 26 Oct 2026.
Thinks first No.
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Open weights
Read on docs.mistral.ai.
Draft a French and Arabic version of a company policy
Analyse a full annual report and list the risks
Files
Run an agent that calls your CRM
Uses your tools