by MistralReleased 13 August 2025
Mistral Medium 3.1, the updated Medium 3 for enterprises that want frontier-level coding, STEM reasoning and multimodal work near Claude Sonnet 3.7 and Llama 4 Maverick, deployable on-prem or privately
Reads about 130 pages · writes up to 100 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 Medium 3.1, the updated Medium 3 for enterprises that want frontier-level coding, STEM reasoning and multimodal work near Claude Sonnet 3.7 and Llama 4 Maverick, deployable on-prem or privately.
Mistral names no languages for Mistral Medium 3.1 (batch). Arabic, French and Darja: not stated.
It reads text, images and PDFs. Up to 131K tokens in one request, about 130 pages. It writes up to 79 000 words at once.
No. Mistral has not published its weights.
Mistral. Released 13 August 2025. It knows the world up to 30 June 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 No.
Read on docs.mistral.ai.
Knows events up to 30 Jun 2025
What it learned stops at this date.
Write and review code for an internal tool
Run an agent that queries your database API
Uses your tools
Extract fields from a scanned form into JSON
Images · Fills your JSON