Magistral Medium 2509

Magistral Medium 2509 is Mistral's reasoning model for enterprise use, with 73.6% on AIME 2024 (single-sample), traceable chain-of-thought, and multilingual reasoning across eight languages. Your use subject to Mistral's Terms & Privacy Policies.

ReasoningTool UseVision (Image)

Use with AI Gateway View docs

TypeScript

Python

import { streamText } from 'ai'

const result = streamText({
  model: 'mistral/magistral-medium',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview About Providers Throughput Latency Uptime Status Similar FAQ

More models by Mistral

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Release Date

mistral/mistral-medium-3.5

256K

0.3s

60tps

$1.50/M

$7.50/M

—

04/29/2026

mistral/devstral-2

256K

0.3s

56tps

$0.40/M

$2/M

—

12/09/2025

mistral/mistral-large-3

256K

0.4s

73tps

$0.50/M

$1.50/M

—

12/02/2025

mistral/codestral-embed

$0.15/M

—

05/28/2025

mistral/ministral-3b

128K

0.2s

147tps

$0.10/M

—

10/16/2024

mistral/mistral-embed

$0.10/M

—

12/11/2023

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Magistral Medium 2509

More models by Mistral