Summary
Vercel's AI Gateway now serves Z.ai's GLM 5.3 FlashX, letting developers call the model through a single API key at roughly 200 tokens per second, with automatic provider fallbacks, spend tracking, and request tracing built in.
What changed
GLM 5.3 FlashX (Z.ai) became callable on Vercel AI Gateway with one-key access, ~200 tok/s throughput, automatic fallbacks, spend tracking, and request traces.
Why it matters
AI Gateway keeps widening its non-OpenAI/Anthropic roster, reinforcing Vercel as a neutral routing layer where teams swap models without re-plumbing auth, billing, or observability. A fast, low-cost model expands price/performance options for latency-sensitive agent and coding workloads.
Evidence excerpt
GLM 5.3 FlashX is now available on AI Gateway — call Z.ai's GLM 5.3 FlashX through Vercel AI Gateway at 200 tokens per second, with one API key, automatic fallbacks, spend tracking, and request traces.