Mistral AI · LLMs & Coding

Mistral Medium 3.5

Catalog data · checked Nov 16, 2026

Mistral Medium 3.5 is a language model from Mistral AI, released in April 2026. It reads text, images and PDF files and writes text, with a context window of 262.1K tokens and up to 262.1K output tokens per answer. It costs $1.5 per million input tokens and $7.5 per million output tokens. That puts it in the upper price range: 67% of the 185 paid language models we track cost less.

Calculate my costCompare

Input price$1.5per 1M tokens
Output price$7.5per 1M tokens
Context window262.1Ktokens per request
Max output262.1Ktokens per answer
ReleasedApr 20266 months ago
WeightsOpencan be self-hosted

What it can do

  • Tool calling
  • Structured output
  • Reasoning mode
  • Image input
  • File input
  • Audio input
  • Video input
  • Image output
  • Audio output
  • Prompt caching

More prices

Cached input (read)$0.15 /1M

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$3.08
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out$0.24
10,000 product descriptions300 input and 200 output tokens per text$19.5
One day of agentic codingabout 3M input and 150K output tokens across many calls$5.63

Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →

Compare Mistral Medium 3.5 with

Questions & answers

How much does Mistral Medium 3.5 cost?

Mistral Medium 3.5 costs $1.5 per 1 million input tokens and $7.5 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of Mistral Medium 3.5?

Mistral Medium 3.5 can process up to 262,144 tokens per request and return up to 262,144 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.

Does Mistral Medium 3.5 support tool calling?

Yes. The API accepts tool (function) definitions and also supports structured JSON output.

Can Mistral Medium 3.5 read images?

Yes, image input is supported, as well as file input (for example PDFs).