For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Logo
Resources
Log inGet a demo
GuidesAPI reference
GuidesAPI reference
    • Get Started
  • Features
    • Projects
    • Cost Governance and Savings
      • Overview
      • Single Provider
      • Priority
      • Performance
      • Intelligent
    • Context Compression
UnifiedAgent HandlerGateway
UnifiedAgent HandlerGateway
Resources
Log inGet a demo
On this page
  • Least latency
  • Lowest cost
FeaturesRouting Policies

Performance strategies

Route by latency or cost across your configured providers.
Was this page helpful?
Previous

Priority

Next

Intelligent routing

Built with

Least latency

Routes to the provider with the lowest observed latency. Gateway tracks rolling latency statistics for each provider and sends new requests to the fastest one.

Best for: Latency-sensitive applications or multi-region provider setups.

Lowest cost

Routes to the cheapest provider for the requested capability. Gateway uses model pricing metadata to automatically select the lowest-cost option.

Best for: Budget-focused workloads where multiple providers offer equivalent models at different prices.

Least Latency and Lowest Cost strategies are configured through the dashboard. The API currently supports Priority (type: "fallback") and Intelligent (type: "intelligent") strategies.