Service tiers now available on AI Gateway
UpdateVerifiedAdded Sep 22, 2026
AI Gateway now supports service tiering. Service tiers let you optimize for latency, throughput, and cost per request to match your use case. Pick a faster tier for interactive workloads (less queueing, higher token throughput), or a lower cost tier for background jobs that can tolerate more latency.
Topics: LLMs, Pricing, Developer tools, Performance
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More AI SDK and AI Gateway releases
Every AI SDK and AI Gateway release| Date | Release | Type |
|---|---|---|
| Jul 21 | Laguna S 2.1 is now available on AI Gateway Update | Update |
| Jul 21 | Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway Update | Update |
| Jul 22 | AI Gateway now supports streaming transcription Beta | Beta |
| Jul 22 | Extend eve agents with installable extensions Update | Update |
| Jul 20 | Configure where run state lives in Vercel Workflows Beta | Beta |
| Jul 23 | Connect to and manage Sandboxes from the dashboard Update | Update |
| Jul 23 | Ling 3.0 Flash is now available on AI Gateway Update | Update |
| Jul 24 | Workflow steps now support extended function durations Beta | Beta |
