Zhipu launches GLM-5.3-FlashX at up to 200 tokens/s, priced 2.5x Flash

pcuenq · x · 2026-09-23

Zhipu has launched GLM-5.3-FlashX (model code: glm-5.3-flashx), a faster version of GLM-5.3-Flash reaching up to 200 tokens/s, available to all API users with Coding Plan users able to opt in. It's priced at 2.5× GLM-5.3-Flash on both the Coding Plan and API. Early users report the speed makes back-and-forth coding noticeably smoother.

Related event: Zhipu Launches GLM-5.3-FlashX at Up to 200 Tokens/s(2 posts)→

Original post →

More from Models

Models channel →