mistralai

Mistral: Mistral Medium 3

mistralai/mistral-medium-3

Our take

AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.

OpenRouter's catalog presents mistralai/mistral-medium-3 as an enterprise-oriented multimodal language model that accepts text, images, and files and returns text. It reports a long context window, tool use, structured outputs, response formatting, and common sampling controls. The catalog also frames the model as offering advanced capability at lower operating cost, but that positioning is source-reported rather than independently established in this pack. Available measurements are limited to selected design-arena categories, so suitability should be validated on real workloads.[1]

Strengths

Accepts text, image, and file inputs while producing text output.[1]
Catalog lists tool calling, structured outputs, response formatting, seeds, and sampling controls.[1]
A long context window may support extended documents and multimodal prompts.[1]

Limitations

Evidence comes only from OpenRouter's catalog; an independent model card was not available in this source pack.[1]
The lower-cost and advanced-capability claims are catalog positioning, not independently verified performance.[1]
Measured results cover selected design-arena categories only; license, safety, deployment, and workload-specific behavior remain unconfirmed.[1]

Where to use it

Potentially useful for assistants that must process long prompts combining text, images, and files.[1]
Worth evaluating for applications needing tool calls or machine-readable structured responses.[1]
Could be tested for cost-sensitive enterprise workloads after task-specific validation.[1]

Sources

[1] OpenRouter catalog · Mistral: Mistral Medium 3Sources checked: Nov 13, 2026

About this model

Description below is the original text supplied by OpenRouter, shown in the source language.

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

Specifications

Model ID: mistralai/mistral-medium-3
Creator: mistralai
Added to OpenRouter: 07.05.2025
Context length: 131,072
Modality: text+image+file->text
Input modalities: text, image, file
Output modalities: text
Token pricing: USD per 1M tokens: in $0.400 / out $2
Knowledge cutoff: 31.03.2025
Expiration date: —

Tasks and capabilities

A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.

Task	Grade	Source-declared capability
General quality	No measurement	—
Coding	No measurement	—
Agents	No measurement	parameters: structured_outputs, tool_choice, tools
Writing	No measurement	output: text
Reasoning	No measurement	—
Document analysis	No measurement	input: file
Vision	No measurement	input: image
Image generation	No measurement	—
Audio	No measurement	—
Video	No measurement	—
Embeddings	No measurement	—

Evaluations

Source	Benchmark	Value	Grade	Data retrieved
Design Arena	models · 3dwin rate 54.7% · rank 102	1,066Elo	CC — below the B band	13.11.2026
Design Arena	models · codecategorieswin rate 48.1% · rank 119	1,059Elo	CC — below the B band	13.11.2026
Design Arena	models · datavizwin rate 46% · rank 115	1,032Elo	CC — below the B band	13.11.2026
Design Arena	models · gamedevwin rate 45.2% · rank 125	1,008Elo	CC — below the B band	13.11.2026
Design Arena	models · uicomponentwin rate 49.6% · rank 120	1,015Elo	CC — below the B band	13.11.2026
Design Arena	models · websitewin rate 47.6% · rank 120	1,072Elo	CC — below the B band	13.11.2026

How grades work

Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.

S — S — top 10% of the cohort
A — A — next 20% of the cohort
B — B — next 30% of the cohort
C — C — below the B band

Providers

Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.

Provider	Context length	Price in /1M	Price out /1M	Latency p50 (30m, s)	Throughput p50 (30m, tok/s)	Uptime (30m)
Mistral	131,072	$0.400	$2	—	—	100%
Mistral	131,072	$0.440	$2.2	—	—	—

Provider data retrieved: 13.11.2026

No published articles identify this model yet.