Performance strategies
Route by latency or cost across your configured providers.
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.