Mistral logo

Mistral: Mistral Medium 3.5 – Chat and Inference API hosted in Europe

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Input Price$1.50/1M tokens
Output Price$7.50/1M tokens
Intelligence29.9
Coding46.9

Specifications

Technical details and pricing.

ProviderMistral
Context Window262,144 tokens
Release DateApr 29, 2026
ModalitiesText, Image, File → Text
CapabilitiesFunction Calling, Structured Outputs, JSON Mode, Vision
AvailabilityChat only

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA74.8%
HLE12.8%
SciCode39.6%
LCR61.0%
IFBench68.8%
Tau294.2%
TerminalBench Hard33.3%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Mistral: Mistral Medium 3.5 good for?

Use Mistral: Mistral Medium 3.5 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Mistral: Mistral Medium 3.5 cost?

Pricing is based on usage. Current rates are $1.50/1M tokens for input and $7.50/1M tokens for output.

Can I try Mistral: Mistral Medium 3.5 for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Mistral: Mistral Medium 3.5 support images or audio?

Mistral: Mistral Medium 3.5 can understand images.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.