Request
This endpoint expects an object.
The network endpoint URL for the model provider
The URN of the project associated with this model provider
Optional description of the model provider
Reference to an API key secret stored in the Secrets service. Create the secret first via secrets API, then pass the secret name here.
Optional list of specific models to enable from this provider
Default body parameters for inference requests. Can be overridden by user requests.
Default headers for inference requests. Can be overridden by user requests.
Required body parameters for inference requests. Cannot be overridden by user requests.
Required headers for inference requests. Cannot be overridden by user requests.
Optional reference to the ModelDeployment ID if this provider is associated with a deployment
Status of the model provider
Literal header format controlling how the API key secret is sent to the upstream. Must contain exactly one <auth_secret> placeholder, which is replaced with the resolved secret value at request time. It is plain text, not a template: no { or } characters or line breaks are allowed. The legacy {{ auth_secret }} spelling is still accepted. Example: 'X-Api-Key: <auth_secret>'. If not set, defaults to 'Authorization: Bearer <auth_secret>'.
For a router that calls models back through the gateway on its caller's behalf. The gateway sends it this provider's stored key and a caller context, the caller's credential sealed so only the gateway can read it, and acts as the caller on each call back that returns the context. A call back with the stored key and no context is refused. Left unset, an update keeps the provider's current setting.
Response
Create or update a model provider
Name of the entity. Name/workspace combo must be unique across all entities. Name must start with a lowercase letter, be 2-63 characters, and use lowercase letters, digits, hyphens, and dots (no consecutive hyphens, cannot end with a hyphen).
The workspace of the entity. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.
The timestamp of model entity creation
The timestamp of the last model entity update
The network endpoint URL for the model provider
Unique identifier for the model provider
The URN of the project associated with this entity.
Optional description of the model provider
Reference to the API key stored in Secrets service
List of models served by this provider with routing information for IGW
Optional list of specific models to enable from this provider. If not set, all discovered models are enabled.
Current status of the model provider, populated by models service
Detailed status message, populated by models service
Default body parameters for inference requests. Can be overridden by user requests.
Default headers for inference requests. Can be overridden by user requests.
Required body parameters for inference requests. Cannot be overridden by user requests.
Required headers for inference requests. Cannot be overridden by user requests.
Optional reference to the ModelDeployment ID if this provider was auto-created for a deployment
Auth context captured at provider creation.
Literal header format controlling how the API key secret is sent to the upstream. Must contain exactly one <auth_secret> placeholder, which is replaced with the resolved secret value at request time. It is plain text, not a template: no { or } characters or line breaks are allowed. The legacy {{ auth_secret }} spelling is still accepted. Example: 'X-Api-Key: <auth_secret>'. If not set, defaults to 'Authorization: Bearer <auth_secret>'.
For a router that calls models back through the gateway on its caller's behalf. The gateway sends it this provider's stored key and a caller context, the caller's credential sealed so only the gateway can read it, and acts as the caller on each call back that returns the context. A call back with the stored key and no context is refused.