Theia API Documentation v1.71.0
    Preparing search index...
    interface AnthropicModelDescription {
        apiKey: undefined | string | true;
        enableStreaming: boolean;
        id: string;
        maxRetries: number;
        maxTokens?: number;
        model: string;
        reasoningApi?: ReasoningApi;
        reasoningSupport?: ReasoningSupport;
        supportsXHighEffort?: boolean;
        url?: string;
        useCaching: boolean;
    }
    Index

    Properties

    apiKey: undefined | string | true

    The key for the model. If 'true' is provided the global Anthropic API key will be used.

    enableStreaming: boolean

    Indicate whether the streaming API shall be used.

    id: string

    The identifier of the model which will be shown in the UI.

    maxRetries: number

    Maximum number of retry attempts when a request fails. Default is 3.

    maxTokens?: number

    Maximum number of tokens to generate. Default is 4096.

    model: string

    The model ID as used by the Anthropic API.

    reasoningApi?: ReasoningApi

    Which Anthropic reasoning API shape to use. Required when reasoningSupport is set.

    • 'effort': adaptive thinking (thinking: { type: 'adaptive' } + output_config: { effort })
    • 'budget': extended thinking (thinking: { type: 'enabled', budget_tokens: N })
    reasoningSupport?: ReasoningSupport

    When set, the UI exposes a reasoning selector and requests are translated to reasoningApi.

    supportsXHighEffort?: boolean

    True on models that accept the Anthropic xhigh effort value.

    url?: string

    The Anthropic API compatible endpoint where the model is hosted. If not provided the default Anthropic endpoint will be used.

    useCaching: boolean

    Indicate whether the model supports prompt caching.