Overview
The high-speed API serving variant of GLM-5.3-Flash, retaining the Flash series’ visual understanding, tool use, and agent capabilities.
GLM-5.3-FlashX
The high-speed API serving variant of GLM-5.3-Flash, retaining the Flash series’ visual understanding, tool use, and agent capabilities.
Z.ai’s official API reference lists the model code `glm-5.3-flashx` in the GLM-5.3-Flash vision-model series; this is a FlashX serving variant, not a separate open-weight release.
MODEL NUMBER108
- First public date
- 2026-09-18
- Organization
- Z.ai
- Family
- GLM
01
Specifications
Only published specifications are shown.
- Input modalities
- Text · Image
- Output modalities
- Text
- Open weights
- No
- Status
- Current
02
Overview
Why it mattered
FlashX separates a serving-speed SKU from the underlying capability band, keeping inference-service changes distinct from base-model weights.
03
Architecture & capabilities
Model capabilities
Native multimodalCodingAgentTool use
04
Release history
Z.ai’s official API reference lists GLM-5.3-FlashX (`glm-5.3-flashx`) in the GLM-5.3-Flash vision-model series; it is a faster serving variant, not a new open-weight release.
View source05
Related models
Select a card to view the related model.
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.