Protected ReadonlychatOptionalheadersProtected ReadonlyloggerOptionalmaxProtected ReadonlyopenProtected ReadonlyparamsOptionalproxyOptionalreasoningOptionalreleasedRelease date (ms since epoch) as reported by the provider, where it reports one. Lets the model lists offer the newest models first instead of ordering them by name.
Protected ReadonlyresponseWhether this model supports provider-native server-side compaction (capability, distinct from whether it is activated).
OptionalserverOptionalserverServer tools this model offers, declared code-level by the provider package.
Note: If you provide these, you must also provide vendor because server tools are vendor-specific.
ReadonlyvendorProvider identifier, used to key per-provider settings (e.g. server tool selections) and the capabilities UI.
ProtectedapplyAugments the Response API settings with the server-side compaction directive when compaction is enabled for the given request. When disabled, the settings are returned unchanged so the default path is byte-for-byte identical.
ProtectedcreateProtectedgetReasoning settings are resolved by getOpenAiRequestSettings. On the Responses API, user-configured reasoning
fields from the request settings (e.g. summary) are kept; the selected level still decides effort.
ProtectedhandleOptionalcancellationToken: CancellationTokenProtectedhandleProtectedhandleOptionalcancellationToken: CancellationTokenProtectedhandleProtectedinitProtectedinitializeProtectedisProtectedprocessOptionalcancellationToken: CancellationToken
See also VS Code
ILanguageModelChatMetadata