Service tiers now available on AI Gateway
Quick Answer
Vercel AI's Gateway now offers service tiers for OpenAI and Gemini models, allowing users to optimize for latency, throughput, and cost.
Quick Take
Users can choose from standard, priority, or flex tiers, with billing adjusted based on the tier used for each request.
Key Points
- Service tiers include standard, priority, and flex options for different workloads.
- Priority tier offers faster processing but at a higher cost.
- Flex tier provides lower costs with potentially higher latency.
- Billing is adjusted based on the actual service tier used for each request.
- Service tiers are applicable across all AI Gateway API formats.
Source Excerpt
AI Gateway now supports service tiers, letting you trade latency and cost on a per-request basis. Billing adjusts automatically based on the tier each request used.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.
