OpenAiModel.ts

// This file was auto-generated by Fern from our API Definition.

import type * as Vapi from "../index.js";

export interface OpenAiModel {
    /** This is the starting state for the conversation. */
    messages?: Vapi.OpenAiMessage[];
    /**
     * These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`.
     *
     * Both `tools` and `toolIds` can be used together.
     */
    tools?: Vapi.OpenAiModelToolsItem[];
    /**
     * These are the tools that the assistant can use during the call. To use transient tools, use `tools`.
     *
     * Both `tools` and `toolIds` can be used together.
     */
    toolIds?: string[];
    /** These are the options for the knowledge base. */
    knowledgeBase?: Vapi.CreateCustomKnowledgeBaseDto;
    /** This is the provider that will be used for the model. */
    provider: Vapi.OpenAiModelProvider;
    /**
     * This is the OpenAI model that will be used.
     *
     * When using Vapi OpenAI or your own Azure Credentials, you have the option to specify the region for the selected model. This shouldn't be specified unless you have a specific reason to do so. Vapi will automatically find the fastest region that make sense.
     * This is helpful when you are required to comply with Data Residency rules. Learn more about Azure regions here https://azure.microsoft.com/en-us/explore/global-infrastructure/data-residency/.
     *
     * @default undefined
     */
    model: Vapi.OpenAiModelModel;
    /** These are the fallback models that will be used if the primary model fails. This shouldn't be specified unless you have a specific reason to do so. Vapi will automatically find the fastest fallbacks that make sense. */
    fallbackModels?: Vapi.OpenAiModelFallbackModelsItem[];
    /**
     * Azure OpenAI doesn't support `maxLength` right now https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/structured-outputs?tabs=python-secure%2Cdotnet-entra-id&pivots=programming-language-csharp#unsupported-type-specific-keywords. Need to strip.
     *
     * - `strip-parameters-with-unsupported-validation` will strip parameters with unsupported validation.
     * - `strip-unsupported-validation` will keep the parameters but strip unsupported validation.
     *
     * @default `strip-unsupported-validation`
     */
    toolStrictCompatibilityMode?: Vapi.OpenAiModelToolStrictCompatibilityMode;
    /**
     * This controls the prompt cache retention policy for models that support extended caching (GPT-4.1, GPT-5 series).
     *
     * - `in_memory`: Default behavior, cache retained in GPU memory only
     * - `24h`: Extended caching, keeps cached prefixes active for up to 24 hours by offloading to GPU-local storage
     *
     * Only applies to models: gpt-5.2, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-chat-latest, gpt-5, gpt-5-codex, gpt-4.1
     *
     * @default undefined (uses API default which is 'in_memory')
     */
    promptCacheRetention?: Vapi.OpenAiModelPromptCacheRetention;
    /**
     * This is the prompt cache key for models that support extended caching (GPT-4.1, GPT-5 series).
     *
     * Providing a cache key allows you to share cached prefixes across requests.
     *
     * @default undefined
     */
    promptCacheKey?: string;
    /** This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. */
    temperature?: number;
    /** This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. */
    maxTokens?: number;
    /**
     * This determines whether we detect user's emotion while they speak and send it as an additional info to model.
     *
     * Default `false` because the model is usually are good at understanding the user's emotion from text.
     *
     * @default false
     */
    emotionRecognitionEnabled?: boolean;
    /**
     * This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai.
     *
     * Default is 0.
     *
     * @default 0
     */
    numFastTurns?: number;
    /**
     * If specified, the system will make a best effort to sample deterministically,
     * such that repeated requests with the same seed and parameters should return the same result.
     * Determinism is not guaranteed.
     *
     * @see https://platform.openai.com/docs/api-reference/chat/create#chat-create-seed
     */
    seed?: number;
    /**
     * An alternative to sampling with temperature, called nucleus sampling,
     * where the model considers the results of the tokens with top_p probability mass.
     * So 0.1 means only the tokens comprising the top 10% probability mass are considered.
     *
     * We generally recommend altering this or temperature but not both.
     *
     * @default 1
     * @see https://platform.openai.com/docs/api-reference/chat/create#chat-create-top_p
     */
    topP?: number;
    /**
     * Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing
     * frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
     *
     * @default 0
     * @see https://platform.openai.com/docs/api-reference/chat/create#chat-create-frequency_penalty
     */
    frequencyPenalty?: number;
    /**
     * Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they
     * appear in the text so far, increasing the model's likelihood to talk about new topics.
     *
     * @default 0
     * @see https://platform.openai.com/docs/api-reference/chat/create#chat-create-presence_penalty
     */
    presencePenalty?: number;
    /**
     * Whether to return log probabilities of the output tokens or not.
     * If true, returns the log probabilities of each output token returned in the content of message.
     *
     * @default false
     * @see https://platform.openai.com/docs/api-reference/chat/create#chat-create-logprobs
     */
    logprobs?: boolean;
    /**
     * An integer between 0 and 20 specifying the number of most likely tokens to return at each
     * token position, each with an associated log probability. logprobs must be set to true if
     * this parameter is used.
     *
     * @see https://platform.openai.com/docs/api-reference/chat/create#chat-create-top_logprobs
     */
    topLogprobs?: number;
    /**
     * Whether to enable parallel function calling during tool use.
     * When set to true, the model can call multiple functions in a single response.
     *
     * @default true
     * @see https://platform.openai.com/docs/guides/function-calling#parallel-function-calling
     */
    parallelToolCalls?: boolean;
    /**
     * Constrains effort on reasoning for reasoning models (o1, o3, etc.).
     * Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
     *
     * Possible values: "low", "medium", "high"
     *
     * @default "medium"
     * @see https://platform.openai.com/docs/api-reference/chat/create#chat-create-reasoning_effort
     */
    reasoningEffort?: Vapi.OpenAiModelReasoningEffort;
}