cd /news/large-language-models/mistral-is-serving-glm-5-2 Ā· home ā€ŗ topics ā€ŗ large-language-models ā€ŗ article
[ARTICLE Ā· art-96574] src=docs.mistral.ai ā†— pub= topic=large-language-models verified=true sentiment=Ā· neutral

Mistral is serving GLM 5.2

Mistral is now hosting Z.ai's GLM 5.2, a third-party open source text model designed for long-context coding and agentic workflows, with a 1 million token context window and 128k max output. Priced at $1.4 per million input tokens, $0.14 per million cached input tokens, and $4.4 per million output tokens, the model is served without modifications by Mistral.

read1 min views2 publishedAug 14, 2026
Mistral is serving GLM 5.2
Image: source

August 6, 2026

BlogPublic PreviewThird-partyv5.2 A third-party open source text model from Z.ai, hosted by Mistral for long-context coding and agentic workflows. The model is served without Mistral modifications.

Speed

Performance

Modalities

Context

1M

Max output

128k

Price

$1.4

Input/M Tokens

$0.14

Cached input/M Tokens

$4.4

Output/M Tokens

Speed

Performance

Modalities

Context

1M

Max output

128k

Price

$1.4

/M Tokens

$0.14

/M Tokens

$4.4

/M Tokens

Other Models

source & further reading
docs.mistral.ai ā€” original article
ā”€ā”€ more in #large-language-models 4 stories Ā· sorted by recency
ā”€ā”€ more on @mistral 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain ā€” perfect for shipping the agent you just read about.

$git push zahid main
ā†’ Live at https://your-agent.zahid.host āœ“
Get free account ā†’ Pricing
from ā‚¬0/mo Ā· no card required
LIVE [news/mistral-is-serving-gā€¦] indexed:0 read:1min 2026-08-14 Ā· ā€”