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

AxAIOpenAIArgs

Defined in: https://github.com/ax-llm/ax/blob/e690b4823b8309e258594064abe941d4cff6ef89/src/ax/ai/openai/api.ts#L142

Extends

  • Omit<AxAIOpenAIBaseArgs<TModel, TEmbedModel, TModelKey, TChatReq>, "config" | "supportFor" | "modelInfo">

Type Parameters

Type ParameterDefault type
TName"openai"
TModelAxAIOpenAIModel
TEmbedModelAxAIOpenAIEmbedModel
TModelKeystring
TChatReq extends AxAIOpenAIChatRequest<TModel>AxAIOpenAIChatRequest<TModel>

Properties

PropertyTypeDescriptionInherited from
apiKey?string-Omit.apiKey
apiURL?string-Omit.apiURL
chatReqUpdater?ChatReqUpdater<TModel, TChatReq>-Omit.chatReqUpdater
chatRespProcessor?ChatRespProcessor-Omit.chatRespProcessor
chatStreamRespProcessor?ChatStreamRespProcessor-Omit.chatStreamRespProcessor
config?Partial<Readonly<AxAIOpenAIConfig<TModel, TEmbedModel>>>--
credentialProfile?string-Omit.credentialProfile
credentialProvider?AxAICredentialProvider-Omit.credentialProvider
modelInfo?AxModelInfo[]--
models?AxAIInputModelList<TModel, TEmbedModel, TModelKey>-Omit.models
nameTName--
options?Readonly<AxAIServiceOptions & object>-Omit.options
promptCacheBreakpoints?booleanWhether the compatible API accepts explicit per-content cache breakpoints.Omit.promptCacheBreakpoints
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.Omit.promptCaching
promptCachingAllModels?booleanApply the compatible prompt-cache wire format without OpenAI model-family gating.Omit.promptCachingAllModels
realtime?RealtimeAdapter<TModel>-Omit.realtime
Docs