Summary
Vercel updated AI Gateway so teams can sort providers behind a model by cost, time to first token, or throughput at request time. The release also exposes routing metadata that shows execution order and deprioritized providers, making gateway policy easier to inspect and tune.
What changed
Vercel added provider sorting controls to AI Gateway for cost-, latency-, and throughput-based routing decisions, plus routing metadata for inspection.
Why it matters
Inference gateways are turning into optimization layers rather than simple API brokers. This matters because teams can now express routing policy around budget, latency, and output speed directly in the gateway, which is increasingly useful for agent loops, high-volume workloads, and multi-provider reliability strategies.
Evidence excerpt
Vercel says AI Gateway can now sort providers behind a model by cost, time to first token, or throughput at request time, and responses include routing metadata that explains execution order and any deprioritized providers.