Context Window

Compare

Gemma 4 31B vs Magistral Medium 2509

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.

Google

Model

Gemma 4 31B

Image inputTool calling

Context window

262K

262,144 tokens · ~197K words

Model page
Mistral

Model

Magistral Medium 2509

Tool calling

Context window

40K

40,000 tokens · ~30K 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.

Gemma 4 31B262K
Magistral Medium 250940K

Gemma 4 31B has about 6.6× the context window of the other in this pair.

Token calculator →Memory savings →

Gemma 4 31B has 555% more context capacity (262K vs 40K tokens).

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use Gemma 4 31B. Its 262K context fits entire documents without chunking (vs 40K).

  • Long output (reports, code files)

    Use Gemma 4 31B. Its 131K max output lets you generate complete artifacts in one request.

Full specs

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

SpecGemma 4 31BMagistral Medium 2509
Context window262,144 tokens (262K)40,000 tokens (40K)
Max output tokens131,072 tokens (131K)40,000 tokens (40K)
Speed tierFastBalanced
VisionYesNo
Function callingYesYes
Extended thinkingYesYes
Prompt cachingNoNo
Batch APINoNo
Release dateApr 2026N/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.

ProviderGemma 4 31B inGemma 4 31B outMagistral Medium 2509 inMagistral Medium 2509 out
Mistral——$2.00/M$5.00/M

Frequently asked questions

Gemma 4 31B has a larger context window: 262K tokens vs 40K. 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