Fallback

The fallback configuration for a route to an inference target. Defines an ordered list of fallback targets to try when a request to the route's target fails, and the conditions that trigger a fallback. A fallback can occur only before the gateway sends the first byte of the response to the caller. After a streaming response starts, the gateway doesn't fall back.

targetFallback

The ordered list of fallback targets. The gateway tries each target in order until a response doesn't match that target's triggers, and returns that response to the caller. If every target fails, the gateway returns the last response. You can specify up to two fallback targets. Each combination of target and model, including the route's target, can appear only once.

Type: Array of FallbackTarget objects

Array Members: Minimum number of 1 item. Maximum number of 2 items.

Required: Yes

circuitBreaker

Specifies whether the gateway temporarily stops sending your requests to a failing target. The circuit breaker tracks each combination of target and model separately. With the circuit breaker enabled, the gateway skips one or more targets and models that fail repeatedly, and your requests go to the next target in the chain. The gateway always tries the last remaining target in the chain. The gateway enables the circuit breaker by default.

Type: CircuitBreakerConfiguration object

Required: No

firstByteTimeoutMilliseconds

The maximum time, in milliseconds, from sending the request to the route's target until the first byte of the response body arrives. If the time expires, the gateway abandons the request and treats it as a FIRST_BYTE_TIMEOUT error. If you don't specify a value, no timeout is enforced.

Type: Integer

Valid Range: Minimum value of 50. Maximum value of 900000.

Required: No

triggerOn

The status codes and errors from the route's target that cause the gateway to send the request to the first fallback target. If you omit triggerOn, the gateway falls back on 5XX status codes and on the CONNECTION_ERROR, FIRST_BYTE_TIMEOUT, and UNROUTABLE errors. If you specify triggerOn, only the status codes and errors that you list trigger a fallback.

Type: FallbackTriggers object

Required: No

Fallback

Contents

See Also