LaunchDevelopersSeptember 18, 2026

GLM 5.3 FlashX lands on Vercel AI Gateway and Hermes Agent

Z.ai's GLM 5.3 FlashX is a high-speed serving option for its multimodal coding model, delivering inference at ~200 tokens per second. Vercel's AI Gateway lists it as zai/glm-5.3-flashx with no markup and no platform fee on inference, including BYOK requests.

2 sources

More stories today

Open the live feed