Mistral AI · LLMs & Coding

Mistral Large 4

Catalog data · checked Nov 16, 2026

Mistral Large 4 is a language model from Mistral AI, released in October 2026. It reads text, images and PDF files and writes text, with a context window of 1.05M tokens and up to 262.1K output tokens per answer. It costs $0.7 per million input tokens and $2.1 per million output tokens. That makes it cheaper than 55% of the 185 paid language models we track.

Calculate my costCompare

Input price$0.7per 1M tokens
Output price$2.1per 1M tokens
Context window1.05Mtokens per request
Max output262.1Ktokens per answer
ReleasedOct 202644 days ago
WeightsClosedAPI only

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)$0.07 /1M

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$1.09
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out$0.109
10,000 product descriptions300 input and 200 output tokens per text$6.3
One day of agentic codingabout 3M input and 150K output tokens across many calls$2.42

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

Compare Mistral Large 4 with

Questions & answers

How much does Mistral Large 4 cost?

Mistral Large 4 costs $0.7 per 1 million input tokens and $2.1 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of Mistral Large 4?

Mistral Large 4 can process up to 1,048,576 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 Large 4 support tool calling?

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

Can Mistral Large 4 read images?

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