Z.ai GLM 5.2
PreviewA third-party Z.ai text model served without Mistral modifications on the Mistral API.
Access details: Mistral API
Versioned identifier · Identity and lifecycle apply to this exact identifier and serving surface.
zai-glm-5-2Capabilities & limits
- Context window
- 1M
- Maximum output
- 128K
- Image input
- Unsupported
- Tool calling
- Supported
- Structured output
- Supported
Documented interfaces and limits. These are not measures of model quality.
Pricing
USD / 1M tokens- Input
- $1.40Derived from the captured rate card's standard token row.
- Output
- $4.40Derived from the captured rate card's standard token row.
USD per million standard text tokens. Detailed cache, batch and other pricing conditions appear in the rate card.
Full rate card 3 rates
Amounts in USD. Check the unit and conditions on each rate.
Input
$1.40 per 1M tokensCached input
$0.14 per 1M tokensOutput
$4.40 per 1M tokensPrice history
Input $1.40 per million tokens
Derived from the captured rate card's standard token row.
Output $4.40 per million tokens
Derived from the captured rate card's standard token row.
Technical details
Technical details have not been verified for this identifier.
6 details not verified
- Parameters
- Active parameters
- Architecture
- Training / knowledge cutoff
- Input modalities
- Output modalities
From Z.ai
Official announcement link: not verified yet.
How they describe it
Provider quote not captured yet.
What they say is different
Provider quote not captured yet.
Verbatim provider claims · not an independent assessment
Release & lifecycle
Availability applies to this exact identifier on Mistral API.
- First API availability
- Aug 6, 2026
- preview
- Observed Sep 13, 2026