Mistral Medium 3.1

Mistral Medium 3.1 was introduced by Mistral AI in mid-2025 as a frontier-class multimodal model designed to improve conversational tone and overall performance. It processes both text and image inputs while generating text responses, making it suitable for workflows that blend visual and linguistic understanding. The model supports a 128k token context window, which gives it room to handle long documents, multi-turn conversations, and retrieval-augmented tasks without frequent truncation.

On Mistral's lifecycle it is marked as Deprecated under the Premier tier with version v25.08, with Mistral guiding new integrations toward its successor. The model supports structured outputs, function calling, predicted outputs, and document question answering, allowing teams to wire it into agentic and tool-using systems. It also handles tool use and image inputs in third-party gateways, indicating practical fit for chat assistants, vision-enabled pipelines, and enterprise applications where deprecated-but-still-served frontier behavior is acceptable.

Mistralmistral-medium-2508mistral-mediumdeprecated

Open provider page Provider docs

Quick Info

Provider: Mistral
Model key: mistral-medium-2508
Release date: Aug 12, 2025
Last updated: Aug 12, 2025
Knowledge cutoff: 2025-05
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.40
Output token cost: $2.00

Limits

Output tokens: 262,144 tokens
Context window: 262,144 tokens

Transparent token rates

Compare Mistral Medium 3.1 pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Mistral Medium 3.1

Mistral

CoverageRelease Notes

Opper AI's dated Mistral release tracker contains an explicit row for Mistral Medium 3.1, listing a release date of August 12, 2025 and an Opper-reported Intelligence index of 15. The tracker groups Medium 3.1 among 31 Mistral releases sorted newest-first, placing it chronologically between Devstral Medium (July 10, 20 The same Opper tracker also documents the lineage context for Mistral Medium 3.1: it is followed in the Medium family by Mistral Medium 3.5 (29 Apr 2026, 256K context) and is distinct from later reasoning-focused Magistral Medium releases (17 Sep 2025 and 18 Sep 2025). The Medium 3.1 row thus corroborates, via an indep

Mistral

CoverageBenchmark

An n8n AI Benchmark page dedicated to Mistral Medium 3.1 describes the model as an updated version of Mistral Medium 3, positioned as a high-performance enterprise-grade language model that aims to deliver frontier-level capabilities at significantly reduced operational cost. According to the page, Mistral Medium 3.1 o The benchmark page lists concrete specifications and n8n's own scores for Mistral Medium 3.1: a 131,072-token context window, a maximum completion size of 41 tokens, an Overall score of 73 (12th placement), Logic 84 (5th), Speed 92 (8th), Tool Use 58 (3rd), Hallucination 74 (10th), Structured Output 83 (3rd), Classific