Project: /docs/reference/js/_project.yaml Book: /docs/reference/_book.yaml page_type: reference

{% comment %} DO NOT EDIT THIS FILE! This is generated by the JS SDK team, and any local changes will be overwritten. Changes should be made in the source code at https://github.com/firebase/firebase-js-sdk {% endcomment %}

ai package

The Firebase AI Web SDK.

Functions

Classes

Interfaces

Variables

Type Aliases

function(app, ...)

getAI(app, options) {:#getai_a94a413}

Returns the default AI instance that is associated with the provided FirebaseApp<!-- -->. If no instance exists, initializes a new instance with the default settings.

<b>Signature:</b>

export declare function getAI(app?: FirebaseApp, options?: AIOptions): AI;

Parameters

<b>Returns:</b>

AI

The default AI instance for the given FirebaseApp<!-- -->.

Example 1

const ai = getAI(app);

Example 2

// Get an AI instance configured to use the Gemini Developer API (via Google AI).
const ai = getAI(app, { backend: new GoogleAIBackend() });

Example 3

// Get an AI instance configured to use the Vertex AI Gemini API.
const ai = getAI(app, { backend: new VertexAIBackend() });

function(ai, ...)

getGenerativeModel(ai, modelParams, requestOptions) {:#getgenerativemodel_c63f46a}

Returns a GenerativeModel class with methods for inference and other functionality.

<b>Signature:</b>

export declare function getGenerativeModel(ai: AI, modelParams: ModelParams | HybridParams, requestOptions?: RequestOptions): GenerativeModel;

Parameters

<b>Returns:</b>

GenerativeModel

getImagenModel(ai, modelParams, requestOptions) {:#getimagenmodel_e1f6645}

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

Returns an ImagenModel class with methods for using Imagen.

Only Imagen 3 models (named imagen-3.0-*<!-- -->) are supported.

<b>Signature:</b>

export declare function getImagenModel(ai: AI, modelParams: ImagenModelParams, requestOptions?: RequestOptions): ImagenModel;

Parameters

<b>Returns:</b>

ImagenModel

Exceptions

If the apiKey or projectId fields are missing in your Firebase config.

getLiveGenerativeModel(ai, modelParams) {:#getlivegenerativemodel_f2099ac}

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Returns a LiveGenerativeModel class for real-time, bidirectional communication.

The Live API is only supported in modern browser windows and Node ><!-- -->= 22.

<b>Signature:</b>

export declare function getLiveGenerativeModel(ai: AI, modelParams: LiveModelParams): LiveGenerativeModel;

Parameters

<b>Returns:</b>

LiveGenerativeModel

Exceptions

If the apiKey or projectId fields are missing in your Firebase config.

getTemplateGenerativeModel(ai, requestOptions) {:#gettemplategenerativemodel_9476bbc}

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Returns a TemplateGenerativeModel class for executing server-side templates.

<b>Signature:</b>

export declare function getTemplateGenerativeModel(ai: AI, requestOptions?: RequestOptions): TemplateGenerativeModel;

Parameters

<b>Returns:</b>

TemplateGenerativeModel

getTemplateImagenModel(ai, requestOptions) {:#gettemplateimagenmodel_9476bbc}

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

Returns a TemplateImagenModel class for executing server-side Imagen templates.

<b>Signature:</b>

export declare function getTemplateImagenModel(ai: AI, requestOptions?: RequestOptions): TemplateImagenModel;

Parameters

<b>Returns:</b>

TemplateImagenModel

function(liveSession, ...)

startAudioConversation(liveSession, options) {:#startaudioconversation_01c8e7f}

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Starts a real-time, bidirectional audio conversation with the model. This helper function manages the complexities of microphone access, audio recording, playback, and interruptions.

Important: This function must be called in response to a user gesture (for example, a button click) to comply with browser autoplay policies<!-- -->.

<b>Signature:</b>

export declare function startAudioConversation(liveSession: LiveSession, options?: StartAudioConversationOptions): Promise<AudioConversationController>;

Parameters

<b>Returns:</b>

Promise<AudioConversationController<!-- -->>

A Promise that resolves with an AudioConversationController<!-- -->.

Exceptions

AIError if the environment does not support required Web APIs (UNSUPPORTED<!-- -->), if a conversation is already active (REQUEST_ERROR<!-- -->), the session is closed (SESSION_CLOSED<!-- -->), or if an unexpected initialization error occurs (ERROR<!-- -->).

DOMException Thrown by navigator.mediaDevices.getUserMedia() if issues occur with microphone access, such as permissions being denied (NotAllowedError<!-- -->) or no compatible hardware being found (NotFoundError<!-- -->). See the MDN documentation for a full list of exceptions.

Example

const liveSession = await model.connect();
let conversationController;

// This function must be called from within a click handler.
async function startConversation() {
  try {
    conversationController = await startAudioConversation(liveSession);
  } catch (e) {
    // Handle AI-specific errors
    if (e instanceof AIError) {
      console.error("AI Error:", e.message);
    }
    // Handle microphone permission and hardware errors
    else if (e instanceof DOMException) {
      console.error("Microphone Error:", e.message);
    }
    // Handle other unexpected errors
    else {
      console.error("An unexpected error occurred:", e);
    }
  }
}

// Later, to stop the conversation:
// if (conversationController) {
//   await conversationController.stop();
// }

AIErrorCode

Standardized error codes that AIError can have.

<b>Signature:</b>

AIErrorCode: {
    readonly ERROR: "error";
    readonly REQUEST_ERROR: "request-error";
    readonly RESPONSE_ERROR: "response-error";
    readonly FETCH_ERROR: "fetch-error";
    readonly SESSION_CLOSED: "session-closed";
    readonly INVALID_CONTENT: "invalid-content";
    readonly API_NOT_ENABLED: "api-not-enabled";
    readonly INVALID_SCHEMA: "invalid-schema";
    readonly NO_API_KEY: "no-api-key";
    readonly NO_APP_ID: "no-app-id";
    readonly NO_MODEL: "no-model";
    readonly NO_PROJECT_ID: "no-project-id";
    readonly PARSE_FAILED: "parse-failed";
    readonly UNSUPPORTED: "unsupported";
}

BackendType

An enum-like object containing constants that represent the supported backends for the Firebase AI SDK. This determines which backend service (Vertex AI Gemini API or Gemini Developer API) the SDK will communicate with.

These values are assigned to the backendType property within the specific backend configuration objects (GoogleAIBackend or VertexAIBackend<!-- -->) to identify which service to target.

<b>Signature:</b>

BackendType: {
    readonly VERTEX_AI: "VERTEX_AI";
    readonly GOOGLE_AI: "GOOGLE_AI";
}

BlockReason

Reason that a prompt was blocked.

<b>Signature:</b>

BlockReason: {
    readonly SAFETY: "SAFETY";
    readonly OTHER: "OTHER";
    readonly BLOCKLIST: "BLOCKLIST";
    readonly PROHIBITED_CONTENT: "PROHIBITED_CONTENT";
}

FinishReason

Reason that a candidate finished.

<b>Signature:</b>

FinishReason: {
    readonly STOP: "STOP";
    readonly MAX_TOKENS: "MAX_TOKENS";
    readonly SAFETY: "SAFETY";
    readonly RECITATION: "RECITATION";
    readonly OTHER: "OTHER";
    readonly BLOCKLIST: "BLOCKLIST";
    readonly PROHIBITED_CONTENT: "PROHIBITED_CONTENT";
    readonly SPII: "SPII";
    readonly MALFORMED_FUNCTION_CALL: "MALFORMED_FUNCTION_CALL";
}

FunctionCallingMode

<b>Signature:</b>

FunctionCallingMode: {
    readonly AUTO: "AUTO";
    readonly ANY: "ANY";
    readonly NONE: "NONE";
}

HarmBlockMethod

This property is not supported in the Gemini Developer API (GoogleAIBackend<!-- -->).

<b>Signature:</b>

HarmBlockMethod: {
    readonly SEVERITY: "SEVERITY";
    readonly PROBABILITY: "PROBABILITY";
}

HarmBlockThreshold

Threshold above which a prompt or candidate will be blocked.

<b>Signature:</b>

HarmBlockThreshold: {
    readonly BLOCK_LOW_AND_ABOVE: "BLOCK_LOW_AND_ABOVE";
    readonly BLOCK_MEDIUM_AND_ABOVE: "BLOCK_MEDIUM_AND_ABOVE";
    readonly BLOCK_ONLY_HIGH: "BLOCK_ONLY_HIGH";
    readonly BLOCK_NONE: "BLOCK_NONE";
    readonly OFF: "OFF";
}

HarmCategory

Harm categories that would cause prompts or candidates to be blocked.

<b>Signature:</b>

HarmCategory: {
    readonly HARM_CATEGORY_HATE_SPEECH: "HARM_CATEGORY_HATE_SPEECH";
    readonly HARM_CATEGORY_SEXUALLY_EXPLICIT: "HARM_CATEGORY_SEXUALLY_EXPLICIT";
    readonly HARM_CATEGORY_HARASSMENT: "HARM_CATEGORY_HARASSMENT";
    readonly HARM_CATEGORY_DANGEROUS_CONTENT: "HARM_CATEGORY_DANGEROUS_CONTENT";
}

HarmProbability

Probability that a prompt or candidate matches a harm category.

<b>Signature:</b>

HarmProbability: {
    readonly NEGLIGIBLE: "NEGLIGIBLE";
    readonly LOW: "LOW";
    readonly MEDIUM: "MEDIUM";
    readonly HIGH: "HIGH";
}

HarmSeverity

Harm severity levels.

<b>Signature:</b>

HarmSeverity: {
    readonly HARM_SEVERITY_NEGLIGIBLE: "HARM_SEVERITY_NEGLIGIBLE";
    readonly HARM_SEVERITY_LOW: "HARM_SEVERITY_LOW";
    readonly HARM_SEVERITY_MEDIUM: "HARM_SEVERITY_MEDIUM";
    readonly HARM_SEVERITY_HIGH: "HARM_SEVERITY_HIGH";
    readonly HARM_SEVERITY_UNSUPPORTED: "HARM_SEVERITY_UNSUPPORTED";
}

ImagenAspectRatio

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

Aspect ratios for Imagen images.

To specify an aspect ratio for generated images, set the aspectRatio property in your ImagenGenerationConfig<!-- -->.

See the documentation for more details and examples of the supported aspect ratios.

<b>Signature:</b>

ImagenAspectRatio: {
    readonly SQUARE: "1:1";
    readonly LANDSCAPE_3x4: "3:4";
    readonly PORTRAIT_4x3: "4:3";
    readonly LANDSCAPE_16x9: "16:9";
    readonly PORTRAIT_9x16: "9:16";
}

ImagenPersonFilterLevel

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

A filter level controlling whether generation of images containing people or faces is allowed.

See the <a href="http://firebase.google.com/docs/vertex-ai/generate-images">personGeneration</a> documentation for more details.

<b>Signature:</b>

ImagenPersonFilterLevel: {
    readonly BLOCK_ALL: "dont_allow";
    readonly ALLOW_ADULT: "allow_adult";
    readonly ALLOW_ALL: "allow_all";
}

ImagenSafetyFilterLevel

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

A filter level controlling how aggressively to filter sensitive content.

Text prompts provided as inputs and images (generated or uploaded) through Imagen on Vertex AI are assessed against a list of safety filters, which include 'harmful categories' (for example, violence<!-- -->, sexual<!-- -->, derogatory<!-- -->, and toxic<!-- -->). This filter level controls how aggressively to filter out potentially harmful content from responses. See the documentation and the Responsible AI and usage guidelines for more details.

<b>Signature:</b>

ImagenSafetyFilterLevel: {
    readonly BLOCK_LOW_AND_ABOVE: "block_low_and_above";
    readonly BLOCK_MEDIUM_AND_ABOVE: "block_medium_and_above";
    readonly BLOCK_ONLY_HIGH: "block_only_high";
    readonly BLOCK_NONE: "block_none";
}

InferenceMode

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Determines whether inference happens on-device or in-cloud.

<b>PREFER_ON_DEVICE:</b> Attempt to make inference calls using an on-device model. If on-device inference is not available, the SDK will fall back to using a cloud-hosted model. <b>ONLY_ON_DEVICE:</b> Only attempt to make inference calls using an on-device model. The SDK will not fall back to a cloud-hosted model. If on-device inference is not available, inference methods will throw. <b>ONLY_IN_CLOUD:</b> Only attempt to make inference calls using a cloud-hosted model. The SDK will not fall back to an on-device model. <b>PREFER_IN_CLOUD:</b> Attempt to make inference calls to a cloud-hosted model. If not available, the SDK will fall back to an on-device model.

<b>Signature:</b>

InferenceMode: {
    readonly PREFER_ON_DEVICE: "prefer_on_device";
    readonly ONLY_ON_DEVICE: "only_on_device";
    readonly ONLY_IN_CLOUD: "only_in_cloud";
    readonly PREFER_IN_CLOUD: "prefer_in_cloud";
}

InferenceSource

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Indicates whether inference happened on-device or in-cloud.

<b>Signature:</b>

InferenceSource: {
    readonly ON_DEVICE: "on_device";
    readonly IN_CLOUD: "in_cloud";
}

Language

The programming language of the code.

<b>Signature:</b>

Language: {
    UNSPECIFIED: string;
    PYTHON: string;
}

LiveResponseType

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

The types of responses that can be returned by LiveSession.receive()<!-- -->.

<b>Signature:</b>

LiveResponseType: {
    SERVER_CONTENT: string;
    TOOL_CALL: string;
    TOOL_CALL_CANCELLATION: string;
    GOING_AWAY_NOTICE: string;
}

Modality

Content part modality.

<b>Signature:</b>

Modality: {
    readonly MODALITY_UNSPECIFIED: "MODALITY_UNSPECIFIED";
    readonly TEXT: "TEXT";
    readonly IMAGE: "IMAGE";
    readonly VIDEO: "VIDEO";
    readonly AUDIO: "AUDIO";
    readonly DOCUMENT: "DOCUMENT";
}

Outcome

Represents the result of the code execution.

<b>Signature:</b>

Outcome: {
    UNSPECIFIED: string;
    OK: string;
    FAILED: string;
    DEADLINE_EXCEEDED: string;
}

POSSIBLE_ROLES

Possible roles.

<b>Signature:</b>

POSSIBLE_ROLES: readonly ["user", "model", "function", "system"]

ResponseModality

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Generation modalities to be returned in generation responses.

<b>Signature:</b>

ResponseModality: {
    readonly TEXT: "TEXT";
    readonly IMAGE: "IMAGE";
    readonly AUDIO: "AUDIO";
}

SchemaType

Contains the list of OpenAPI data types as defined by the OpenAPI specification

<b>Signature:</b>

SchemaType: {
    readonly STRING: "string";
    readonly NUMBER: "number";
    readonly INTEGER: "integer";
    readonly BOOLEAN: "boolean";
    readonly ARRAY: "array";
    readonly OBJECT: "object";
}

ThinkingLevel

A preset that controls the model's "thinking" process. Use ThinkingLevel.LOW for faster responses on less complex tasks, and ThinkingLevel.HIGH for better reasoning on more complex tasks.

<b>Signature:</b>

ThinkingLevel: {
    MINIMAL: string;
    LOW: string;
    MEDIUM: string;
    HIGH: string;
}

URLRetrievalStatus

The status of a URL retrieval.

<b>URL_RETRIEVAL_STATUS_UNSPECIFIED:</b> Unspecified retrieval status. <b>URL_RETRIEVAL_STATUS_SUCCESS:</b> The URL retrieval was successful. <b>URL_RETRIEVAL_STATUS_ERROR:</b> The URL retrieval failed. <b>URL_RETRIEVAL_STATUS_PAYWALL:</b> The URL retrieval failed because the content is behind a paywall. <b>URL_RETRIEVAL_STATUS_UNSAFE:</b> The URL retrieval failed because the content is unsafe.

<b>Signature:</b>

URLRetrievalStatus: {
    URL_RETRIEVAL_STATUS_UNSPECIFIED: string;
    URL_RETRIEVAL_STATUS_SUCCESS: string;
    URL_RETRIEVAL_STATUS_ERROR: string;
    URL_RETRIEVAL_STATUS_PAYWALL: string;
    URL_RETRIEVAL_STATUS_UNSAFE: string;
}

AIErrorCode

Standardized error codes that AIError can have.

<b>Signature:</b>

export type AIErrorCode = (typeof AIErrorCode)[keyof typeof AIErrorCode];

BackendType

Type alias representing valid backend types. It can be either 'VERTEX_AI' or 'GOOGLE_AI'<!-- -->.

<b>Signature:</b>

export type BackendType = (typeof BackendType)[keyof typeof BackendType];

BlockReason

Reason that a prompt was blocked.

<b>Signature:</b>

export type BlockReason = (typeof BlockReason)[keyof typeof BlockReason];

FinishReason

Reason that a candidate finished.

<b>Signature:</b>

export type FinishReason = (typeof FinishReason)[keyof typeof FinishReason];

FunctionCallingMode

<b>Signature:</b>

export type FunctionCallingMode = (typeof FunctionCallingMode)[keyof typeof FunctionCallingMode];

HarmBlockMethod

This property is not supported in the Gemini Developer API (GoogleAIBackend<!-- -->).

<b>Signature:</b>

export type HarmBlockMethod = (typeof HarmBlockMethod)[keyof typeof HarmBlockMethod];

HarmBlockThreshold

Threshold above which a prompt or candidate will be blocked.

<b>Signature:</b>

export type HarmBlockThreshold = (typeof HarmBlockThreshold)[keyof typeof HarmBlockThreshold];

HarmCategory

Harm categories that would cause prompts or candidates to be blocked.

<b>Signature:</b>

export type HarmCategory = (typeof HarmCategory)[keyof typeof HarmCategory];

HarmProbability

Probability that a prompt or candidate matches a harm category.

<b>Signature:</b>

export type HarmProbability = (typeof HarmProbability)[keyof typeof HarmProbability];

HarmSeverity

Harm severity levels.

<b>Signature:</b>

export type HarmSeverity = (typeof HarmSeverity)[keyof typeof HarmSeverity];

ImagenAspectRatio

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

Aspect ratios for Imagen images.

To specify an aspect ratio for generated images, set the aspectRatio property in your ImagenGenerationConfig<!-- -->.

See the documentation for more details and examples of the supported aspect ratios.

<b>Signature:</b>

export type ImagenAspectRatio = (typeof ImagenAspectRatio)[keyof typeof ImagenAspectRatio];

ImagenPersonFilterLevel

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

A filter level controlling whether generation of images containing people or faces is allowed.

See the <a href="http://firebase.google.com/docs/vertex-ai/generate-images">personGeneration</a> documentation for more details.

<b>Signature:</b>

export type ImagenPersonFilterLevel = (typeof ImagenPersonFilterLevel)[keyof typeof ImagenPersonFilterLevel];

ImagenSafetyFilterLevel

Warning: This API is now obsolete.

All Imagen models are deprecated and will shut down as early as June 2026. As a replacement, you can migrate your apps to use Gemini Image models (the "Nano Banana" models)<!-- -->.

A filter level controlling how aggressively to filter sensitive content.

Text prompts provided as inputs and images (generated or uploaded) through Imagen on Vertex AI are assessed against a list of safety filters, which include 'harmful categories' (for example, violence<!-- -->, sexual<!-- -->, derogatory<!-- -->, and toxic<!-- -->). This filter level controls how aggressively to filter out potentially harmful content from responses. See the documentation and the Responsible AI and usage guidelines for more details.

<b>Signature:</b>

export type ImagenSafetyFilterLevel = (typeof ImagenSafetyFilterLevel)[keyof typeof ImagenSafetyFilterLevel];

InferenceMode

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Determines whether inference happens on-device or in-cloud.

<b>Signature:</b>

export type InferenceMode = (typeof InferenceMode)[keyof typeof InferenceMode];

InferenceSource

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Indicates whether inference happened on-device or in-cloud.

<b>Signature:</b>

export type InferenceSource = (typeof InferenceSource)[keyof typeof InferenceSource];

Language

The programming language of the code.

<b>Signature:</b>

export type Language = (typeof Language)[keyof typeof Language];

LanguageModelMessageContentValue

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Content formats that can be provided as on-device message content.

<b>Signature:</b>

export type LanguageModelMessageContentValue = ImageBitmapSource | AudioBuffer | BufferSource | string;

LanguageModelMessageRole

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Allowable roles for on-device language model usage.

<b>Signature:</b>

export type LanguageModelMessageRole = 'system' | 'user' | 'assistant';

LanguageModelMessageType

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Allowable types for on-device language model messages.

<b>Signature:</b>

export type LanguageModelMessageType = 'text' | 'image' | 'audio';

LiveResponseType

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

The types of responses that can be returned by LiveSession.receive()<!-- -->. This is a property on all messages that can be used for type narrowing. This property is not returned by the server, it is assigned to a server message object once it's parsed.

<b>Signature:</b>

export type LiveResponseType = (typeof LiveResponseType)[keyof typeof LiveResponseType];

Modality

Content part modality.

<b>Signature:</b>

export type Modality = (typeof Modality)[keyof typeof Modality];

Outcome

Represents the result of the code execution.

<b>Signature:</b>

export type Outcome = (typeof Outcome)[keyof typeof Outcome];

Part

Content part - includes text, image/video, or function call/response part types.

<b>Signature:</b>

export type Part = TextPart | InlineDataPart | FunctionCallPart | FunctionResponsePart | FileDataPart | ExecutableCodePart | CodeExecutionResultPart;

ResponseModality

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Generation modalities to be returned in generation responses.

<b>Signature:</b>

export type ResponseModality = (typeof ResponseModality)[keyof typeof ResponseModality];

Role

Role is the producer of the content.

<b>Signature:</b>

export type Role = (typeof POSSIBLE_ROLES)[number];

SchemaType

Contains the list of OpenAPI data types as defined by the OpenAPI specification

<b>Signature:</b>

export type SchemaType = (typeof SchemaType)[keyof typeof SchemaType];

TemplateTool

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Defines a tool that a TemplateGenerativeModel can call to access external knowledge. Only function declarations are currently supported for templates.

<b>Signature:</b>

export type TemplateTool = TemplateFunctionDeclarationsTool;

ThinkingLevel

A preset that controls the model's "thinking" process. Use ThinkingLevel.LOW for faster responses on less complex tasks, and ThinkingLevel.HIGH for better reasoning on more complex tasks.

<b>Signature:</b>

export type ThinkingLevel = (typeof ThinkingLevel)[keyof typeof ThinkingLevel];

Tool

Defines a tool that model can call to access external knowledge.

<b>Signature:</b>

export type Tool = FunctionDeclarationsTool | GoogleSearchTool | CodeExecutionTool | URLContextTool;

TypedSchema

A type that includes all specific Schema types.

<b>Signature:</b>

export type TypedSchema = IntegerSchema | NumberSchema | StringSchema | BooleanSchema | ObjectSchema | ArraySchema | AnyOfSchema;

URLRetrievalStatus

The status of a URL retrieval.

<b>URL_RETRIEVAL_STATUS_UNSPECIFIED:</b> Unspecified retrieval status. <b>URL_RETRIEVAL_STATUS_SUCCESS:</b> The URL retrieval was successful. <b>URL_RETRIEVAL_STATUS_ERROR:</b> The URL retrieval failed. <b>URL_RETRIEVAL_STATUS_PAYWALL:</b> The URL retrieval failed because the content is behind a paywall. <b>URL_RETRIEVAL_STATUS_UNSAFE:</b> The URL retrieval failed because the content is unsafe.

<b>Signature:</b>

export type URLRetrievalStatus = (typeof URLRetrievalStatus)[keyof typeof URLRetrievalStatus];