Interface AsyncBatch

website/worker-configuration.d.ts:3723–3767

    presence_penalty?: number;
}
interface AsyncBatch {
    requests?: {
        /**
         * User-supplied reference. This field will be present in the response as well it can be used to reference the request and response. It's NOT validated to be unique.
         */
        external_reference?: string;
        /**
         * Prompt for the text generation model
         */
        prompt?: string;
        /**
         * If true, the response will be streamed back incrementally using SSE, Server Sent Events.
         */
        stream?: boolean;
        /**
         * The maximum number of tokens to generate in the response.
         */
        max_tokens?: number;
        /**
         * Controls the randomness of the output; higher values produce more random results.
         */
        temperature?: number;
        /**
         * Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses.
         */
        top_p?: number;
        /**
         * Random seed for reproducibility of the generation.
         */
        seed?: number;
        /**
         * Penalty for repeated tokens; higher values discourage repetition.
         */
        repetition_penalty?: number;
        /**
         * Decreases the likelihood of the model repeating the same lines verbatim.
         */
        frequency_penalty?: number;
        /**
         * Increases the likelihood of the model introducing new topics.
         */
        presence_penalty?: number;
        response_format?: JSONMode;
    }[];
}
type Ai_Cf_Meta_Llama_3_3_70B_Instruct_Fp8_Fast_Output = {
    /**
     * The generated text response from the model