Skip to main content
Mistral AI

Magistral Medium (latest) pricing, context window and limits

Magistral Medium (latest) costs $2 per million input tokens and $5 per million output tokens at Mistral AI list price. It accepts up to 128,000 tokens of context and returns up to 16,384 tokens.

  • Model id magistral-medium-latest
  • Snapshot

What does Magistral Medium (latest) cost?​

List prices in US dollars per million tokens
Input$2
Output$5
Cached input (read)—
Cache write—

US dollars per million tokens. A dash means no price is published.

How much can Magistral Medium (latest) read and write?​

Token limits
Context window128,000
Max output16,384

What can Magistral Medium (latest) do?​

Capabilities
Vision (image input)No
Tool callingYes
Structured outputNo
ReasoningYes
Inputtext
Outputtext

What does a request to Magistral Medium (latest) cost?​

Cost of example requests at list price, in US dollars
A typical request: 1,000 tokens in, 500 out$0.0045
A long request: 10,000 tokens in, 1,000 out$0.025
1,000 typical requests$4.5
1 million tokens in and 1 million out$7

Among 32 Mistral AI models with a published price, Magistral Medium (latest) is the 29th cheapest by input price. Its context window is the 17th largest of 32. List prices only; discounts, batch prices and prices above 200K tokens are not shown.

How do I call Magistral Medium (latest) through DVARA?​

Configure the mistral provider in the DVARA LLM Gateway and send the model id magistral-medium-latest. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.

In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.

What should I check before relying on this data?​

The weekly review marked this entry. A person saw each mark and kept the model listed.

  • The price differs by more than 1% from another published price list.

Which other Mistral AI models are there?​

All 34 Mistral AI models · Search the full catalogue

Which models from other providers are similar to Magistral Medium (latest)?​

These are the closest in context window and input price, one per provider.

Snapshot 4 October 2026. DVARA reviews every price weekly before it is published. Get the whole catalogue as models.json. Prices are list prices in US dollars per million tokens; check your provider contract before you budget.