GLM 5.2 Fast via Wafer now available on AI Gateway

Short summary

Vercel's AI Gateway now supports GLM 5.2 Fast via Wafer, delivering 2x higher throughput than competitors (170+ tok/s small context, 200+ tok/s large context). The unified API offers usage tracking, cost reporting, and failover at provider pricing with zero platform fees. Developers can try it immediately in the model playground.

• •GLM 5.2 Fast launched on Vercel AI Gateway with 2x throughput advantage via Wafer
• •170+ tok/s small context, 200+ tok/s large context with unified API and failover
• •Provider pricing with no markup or platform fees; instant playground access

Generated with AI, which can make mistakes.