Member Junction
    Preparing search index...

    Interface AIConfig

    interface AIConfig {
        apiKey: string;
        effortLevel?: number;
        maxTokens?: number;
        model: string;
        modelOverrides?: Record<string, ModelOverride>;
        pricing?: TokenPricingConfig;
        provider:
            | "gemini"
            | "openai"
            | "anthropic"
            | "groq"
            | "mistral"
            | "vertex"
            | "azure"
            | "cerebras"
            | "openrouter"
            | "xai"
            | "bedrock";
        rateLimits?: RateLimitConfig;
        requestsPerMinute?: number;
        retry?: RetryConfig;
        temperature?: number;
    }
    Index

    Properties

    apiKey effortLevel? maxTokens? model modelOverrides? pricing? provider rateLimits? requestsPerMinute? retry? temperature?

    Properties

    apiKey: string
    effortLevel?: number
    maxTokens?: number
    model: string
    modelOverrides?: Record<string, ModelOverride>

    Per-purpose model overrides. Keys are purpose names (e.g., "fkPruning"). Each override can specify a different model, temperature, maxTokens, and effortLevel. If a purpose is not listed, the default model/settings from the parent AIConfig are used.

    pricing?: TokenPricingConfig
    provider:
        | "gemini"
        | "openai"
        | "anthropic"
        | "groq"
        | "mistral"
        | "vertex"
        | "azure"
        | "cerebras"
        | "openrouter"
        | "xai"
        | "bedrock"
    rateLimits?: RateLimitConfig

    Rate limiting configuration for API calls

    requestsPerMinute?: number

    Use rateLimits.requestsPerMinute instead

    retry?: RetryConfig

    Retry configuration for failed API calls (429, network errors)

    temperature?: number

    Settings

    Member Visibility

    On This Page

    Properties