Back to devstral
Mistral AI /

Devstral Medium
Devstral Medium

API OnlyChat & ReasoningtextUpdated July 10, 2025
Some details or benchmark scores on this page are self-reported by developers and unconfirmed.

Devstral Medium

📌 Model Overview

Mistral coding agent model for repository tasks and software engineering workflows

Devstral Medium is a Api Only model developed by Mistral AI, released on 2025-07-10. It is designed primarily for Chat Reasoning workloads. Featuring a 128K tokens context window and Undisclosed parameter count, it offers robust performance for enterprise integration, developers, and researchers.


✨ Key Features & Capabilities

Specification Table
FeatureDescription
Context Window128K tokens capacity for extended prompts and multi-turn workflows
Primary TaskOptimized for Chat Reasoning
Deploymentapi-only
Modalitytext
Max OutputMax Output: 128K tokens
Tool / function calling supportTool / function calling support

⚙️ Technical Specifications

Specification Table
SpecificationDetails
Developer / LabMistral AI
Release Date2025-07-10
Model TypeApi Only
ParametersUndisclosed
Context Window128K tokens
LicenseProprietary
Model Familydevstral

📊 Benchmarks & Performance

Specification Table
BenchmarkScoreSource
SWE-Bench Verified61.6%Independent Eval

💰 Pricing

Specification Table
Tier / UnitRate (USD)
1M input tokens$0.4
1M output tokens$2

📜 License & Usage

This model is governed by the Proprietary license. Please check official developer guidelines before commercial deployment.

Key Features

Max Output: 128K tokens

Feature 01

Tool / function calling support

Feature 02

You might also want to compare

Verified Sources

Tags

tool-calling

Model Specs

api-only

Parameters

Undisclosed

Context Window

128K tokens

License

Proprietary

Deployment

api-only

Pricing

  • 1M input tokens$0.4
  • 1M output tokens$2

as of 2026-07-26

Lineage

Model Family

Part of the devstral family

Curator Notes

Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model