Context Window

Compare

Devstral Medium 2507 vs GLM 5

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

Devstral Medium 2507

Tool calling

Context window

128K

128,000 tokens · ~96K words

Model page
Z Ai

Model

GLM 5

Tool calling

Context window

203K

202,752 tokens · ~152K 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.

Devstral Medium 2507128K
GLM 5203K

GLM 5 has about 1.6× the context window of the other in this pair.

Token calculator →Memory savings →

GLM 5 has 58% more context capacity (202K vs 128K tokens). Devstral Medium 2507 is 60% cheaper on input.

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use GLM 5. Its 202K context fits entire documents without chunking (vs 128K).

  • RAG / high-volume retrieval

    Use Devstral Medium 2507. Input tokens are 60% cheaper — critical when sending large retrieved contexts.

Full specs

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

SpecDevstral Medium 2507GLM 5
Context window128,000 tokens (128K)202,752 tokens (202K)
Max output tokens128,000 tokens (128K)128,000 tokens (128K)
Speed tierBalancedBalanced
VisionNoNo
Function callingYesYes
Extended thinkingNoYes
Prompt cachingNoYes
Batch APINoNo
Release dateN/AFeb 2026

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.

ProviderDevstral Medium 2507 inDevstral Medium 2507 outGLM 5 inGLM 5 out
Baseten——$0.950/M$3.15/M
Mistral$0.400/M$2.00/M——
Openrouter——$0.800/M$2.56/M
Z Ai——$1.00/M$3.20/M

Frequently asked questions

GLM 5 has a larger context window: 202K tokens vs 128K. 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