AI BriefingVercel AI Gateway Adds Support for Z.ai's GLM 5.3 FlashX Model
Key point
Vercel AI Gateway now supports Z.ai's GLM 5.3 FlashX model, which enables ultra-fast inference.
Details
Vercel AI Gateway has begun supporting GLM 5.3 FlashX, Z.ai's multimodal coding model. This model provides an inference speed of approximately 200 tokens per second, accelerating streaming responses.
Key Features and Use Cases
The high serving speed of GLM 5.3 FlashX is particularly useful for coding agents, tool loops, and interactive applications where users wait for generated output. Users can invoke the model via the zai/glm-5.3-flashx identifier across various API formats and coding agents.
AI Gateway Features and Cost Policy
AI Gateway provides a unified API for model invocation, usage and cost tracking, and retry and failover configuration. This ensures availability beyond the provider level and includes built-in custom reporting, API key budget management, and routing rules.
Regarding costs, AI Gateway reflects the provider's pricing directly and does not impose additional margins or inference platform fees. The same policy applies to BYOK (Bring Your Own Key) requests.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.