The identifier of the model which will be shown in the UI, of the form chatgpt/<model>.
Maximum number of retry attempts when a request fails.
The model ID as used by the ChatGPT endpoint.
OptionalserverResolved global/provider default for server-side compaction.
OptionalserverOptional input-token threshold; unset lets the provider choose.
Describes a model served by the ChatGPT subscription. The endpoint, the authentication and the request shape are fixed by the ChatGPT contract, so this carries no endpoint configuration.