Define routing rules across providers and regions. Requests automatically fall over to healthy backends when upstreams degrade, time out, or rate limit.
Обзор возможностей
multi
providers per model
live
health-aware routing
1 flow
no client code change
Ключевые ценностные моменты для практических рабочих процессов.
Преимущество
01
Reduced single-provider risk
When one upstream goes down, traffic shifts to fallback providers instead of impacting your end users.
Преимущество
02
Latency-aware routing
Prefer providers with the lowest observed latency and success rate over a rolling window.
Преимущество
03
Per-model routing rules
Tune routing priority, fallback chain, and timeout policy independently for each model.
Простой путь из 3 шагов для интеграции этой возможности в вызовы шлюза, политики маршрутизации и контроль биллинга.
Шаг 1
Define route
Map each model id to a primary provider plus an ordered fallback chain.
Шаг 2
Set policy
Pick timeouts, retry limits, and health thresholds that match your latency and reliability budget.
Шаг 3
Monitor and tune
Inspect provider health and fallback rate in the dashboard and refine rules as traffic shifts.
Upstream timeouts, 5xx responses, rate limit errors, or breaching the health threshold all trigger fallback to the next provider in the chain.
Yes. Per-request and per-key policy overrides let you force a specific provider when needed.
Следующий шаг
Начните с документации, каталога моделей или панели управления и проверьте эту возможность на реальном трафике.