GLM 5.3 FlashX now available on AI Gateway
By Steven Van ·
Z.ai's coding model gets a ~200 tokens-per-second serving option on Vercel's AI Gateway, usable via API or coding agents.
Z.ai's GLM 5.3 FlashX model is now available on Vercel AI Gateway. It's a high-speed serving option for the multimodal coding model, running inference at roughly 200 tokens per second for faster streamed responses, which the gateway notes is useful for coding agents, tool loops, and other interactive uses where output speed is visible to the user.
The model is available as zai/glm-5.3-flashx across API formats and in coding agents. To use it in an agent, run vercel ai-gateway setup to create a key and configure the agent, then select zai/glm-5.3-flashx within it. It can also be tried in the model playground.