Context Window

Compare

Mistral Large 4 vs Mistral Small 3 2 2506

This page is context-first: how much text each model can take in one request. Full specs adds capabilities and limits; the pricing matrix below is only about $/million tokens from hosts that list both models.

Mistral

Model

Mistral Large 4

Image inputTool calling

Context window

524K

524,288 tokens · ~393K words

Model page
Mistral

Model

Mistral Small 3 2 2506

Image inputTool calling

Context window

131K

131,072 tokens · ~98K words

Model page

Context window · side by side

Bar length is relative to the larger of the two windows (100% = max of this pair). This is not pricing.

Mistral Large 4524K
Mistral Small 3 2 2506131K

Mistral Large 4 has about 4× the context window of the other in this pair.

Token calculator →Memory savings →

Mistral Large 4 has 300% more context capacity (524K vs 131K tokens). Mistral Small 3 2 2506 is 91% cheaper on input.

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use Mistral Large 4. Its 524K context fits entire documents without chunking (vs 131K).

  • RAG / high-volume retrieval

    Use Mistral Small 3 2 2506. Input tokens are 91% cheaper — critical when sending large retrieved contexts.

Full specs

Context, output, capabilities, and dates. Green highlights the favorable value where we compute a winner.

SpecMistral Large 4Mistral Small 3 2 2506
Context window524,288 tokens (524K)131,072 tokens (131K)
Max output tokensN/A131,072 tokens (131K)
Speed tierDeepBalanced
VisionYesYes
Function callingYesYes
Extended thinkingYesNo
Prompt cachingYesNo
Batch APINoNo
Release dateN/AN/A

Pricing matrix

Dollar rates only: hosts that list both models, per 1M tokens. For how much text fits, use the context section above — not this table.

ProviderMistral Large 4 inMistral Large 4 outMistral Small 3 2 2506 inMistral Small 3 2 2506 out
Mistral$0.680/M$2.09/M$0.060/M$0.180/M

Frequently asked questions

Mistral Large 4 has a larger context window: 524K tokens vs 131K. For long documents, large codebases, or extended agent sessions, the larger context window reduces the need to chunk inputs or summarize history.

Powered by Mem0

Use a smaller model.
Get better results.

Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.

Calculate your savingsLearn about Mem0

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model