model field accepts three forms.
Model reference syntax
| Form | Example | Meaning |
|---|---|---|
| Short (pass-through) | gpt-4o-mini | Sent as-is to the selected registry. The load balancer picks among the consumer’s registries. |
| Provider-qualified | @openai/gpt-4o | Restrict routing to registries of provider openai, then pick. |
| Pool reference | pool:my-pool | Route via the consumer’s enabled load-balancing pool whose pool_alias matches (case-insensitive), across the pool’s members. Inline routing only. |
Model policies
Consumers and roles can constrain which models are reachable per registry withmodel_policies:
allowed— the allow-list of models for that registry. Empty/omitted means all models are permitted.default— used when the request names no model; it must be a member ofallowed.
Resolution order
- Parse the
modelreference (short / qualified / pool). - Narrow the candidate registries (the consumer’s
registry_idsor the pool members, filtered by provider for qualified refs). - Apply
model_policies— reject disallowed models; fill in thedefaultwhen none was given. - Hand the candidates to the load balancer to pick one, with fallback on failure.