AxAIOpenAIBaseArgs Generated TypeScript API reference. typescript api api/reference build/apidocs/Interface.AxAIOpenAIBaseArgs.md interface AxAIOpenAIBaseArgs

AxAIOpenAIBaseArgs

Defined in: https://github.com/ax-llm/ax/blob/e690b4823b8309e258594064abe941d4cff6ef89/src/ax/ai/openai/api.ts#L281

Type Parameters

Type Parameter
TModel
TEmbedModel
TModelKey
TChatReq extends AxAIOpenAIChatRequest<TModel>

Properties

PropertyTypeDescription
apiKey?string-
apiURL?string-
chatReqUpdater?ChatReqUpdater<TModel, TChatReq>-
chatRespProcessor?ChatRespProcessor-
chatStreamRespProcessor?ChatStreamRespProcessor-
configReadonly<AxAIOpenAIConfig<TModel, TEmbedModel>>-
credentialProfile?string-
credentialProvider?AxAICredentialProvider-
modelInforeadonly AxModelInfo[]-
models?AxAIInputModelList<TModel, TEmbedModel, TModelKey>-
options?Readonly<AxAIServiceOptions & object>-
promptCacheBreakpoints?booleanWhether the compatible API accepts explicit per-content cache breakpoints.
promptCaching?booleanOpt in to OpenAI prompt caching on GPT-5.6+ models. Off by default because this request builder is shared: Azure OpenAI is typed on the same model enum, so a gpt-5.6-* deployment would otherwise pick up parameters its API version may reject. Official OpenAI and explicitly compatible named profiles opt in deliberately.
promptCachingAllModels?booleanApply the compatible prompt-cache wire format without OpenAI model-family gating.
realtime?RealtimeAdapter<TModel>-
supportFor| AxAIFeatures | (model: TModel) => AxAIFeatures-
Docs