Key Info
Z.ai's faster GLM-5.3-Flash (model code: glm-5.3-flashx) is now live, delivering up to 200 tokens/s throughput.
Highlights
- Speed: up to 200 tokens/s, faster than the standard GLM-5.3-Flash.
- Pricing: 2.5× the cost of GLM-5.3-Flash on both the Coding Plan and API.
- Availability: open to all API users; Coding Plan users can apply via the provided link.