Aiter AI World
EnglishSign inGet started
Loading…

Provider routing

How a request chooses a provider, and the preferences you can set per request.

Base URL for this deployment: https://www.aiteraiworld.com/api/v1

How routing works

  1. The model id is resolved, including aliases, and the key's model allowlist is checked.
  2. Every endpoint for the model is considered. Disabled providers, providers excluded by your preferences, endpoints that cannot honour requested parameters and endpoints above your price ceiling are dropped.
  3. Your own provider credentials (BYOK) come first, then explicit order, then the provider that served your last request for this model, then the configured sort.
  4. Credit is reserved for the worst case, the first candidate is called, and failures before the first byte fall through to the next candidate. Unused credit is released when the record settles.

The provider object

json
{
  "model": "author/model",
  "messages": [{ "role": "user", "content": "Hello" }],
  "provider": {
    "order": ["aiter-server"],
    "ignore": [],
    "allow_fallbacks": true,
    "sort": "price",
    "max_price": { "prompt": 1, "completion": 4 },
    "require_parameters": true,
    "data_collection": "deny"
  }
}
PreferenceMeaning
onlyConsider only these provider ids.
ignoreNever use these provider ids.
orderTry providers in this order before the default sort.
allow_fallbacksEnabled by default. When set to false, only the first candidate is tried.
sortprice, latency (default) or throughput.
max_priceCeilings in USD per million tokens, per price component (prompt, completion, cached, reasoning).
require_parametersSkip endpoints that do not support every sampling or tool parameter in the request.
data_collectiondeny restricts routing to providers that do not train on prompts.
cacheOpt in to the exact-match response cache; see Caching and idempotency.

Provider ids are shown on the providers page and on each model page. A 503 no_eligible_provider response means your preferences excluded every endpoint.