Dispatch
Vercel AI Gateway adds service tiers for latency vs cost tradeoffs
AI Gateway now supports service tiering, letting developers pick a faster tier with less queueing for interactive workloads or a cheaper tier for batch and background jobs. This mirrors the priority/flex tier split the model providers themselves have shipped, but at the gateway layer so it works across providers uniformly. Vercel also added Poolside's Laguna S 2.1 in free 256K-context and paid 1M-context variants the same week.
Source
↳ Follow the thread