GenerationConfig interface

Config options for content-related requests

Signature:

export interface GenerationConfig 

Properties

GenerationConfig.candidateCount

Not supported in Gemini 3.x and later models. The model will ignore this parameter if it's included in a request. Make parallel requests instead.

Signature:

candidateCount?: number;

GenerationConfig.frequencyPenalty

Not supported in Gemini 3.x and later models. Requests that include this parameter will fail with a 400 error. Omit this parameter.

Signature:

frequencyPenalty?: number;

GenerationConfig.imageConfig

Configuration options for generating images with Gemini models.

Signature:

imageConfig?: ImageConfig;

GenerationConfig.maxOutputTokens

Signature:

maxOutputTokens?: number;

GenerationConfig.presencePenalty

Not supported in Gemini 3.x and later models. Requests that include this parameter will fail with a 400 error. Omit this parameter.

Signature:

presencePenalty?: number;

GenerationConfig.responseJsonSchema

Output schema of the generated response. This is an alternative to responseSchema that accepts [JSON Schema](https://json-schema.org/).

If set, responseSchema must be omitted, but responseMimeType is required and must be set to application/json.

Signature:

responseJsonSchema?: {
        [key: string]: unknown;
    };

GenerationConfig.responseMimeType

Output response MIME type of the generated candidate text. Supported MIME types are text/plain (default, text output), application/json (JSON response in the candidates), and text/x.enum.

Signature:

responseMimeType?: string;

GenerationConfig.responseModalities

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.

• Multimodal response generation is only supported by some Gemini models and versions; see model versions. - Only image generation (ResponseModality.IMAGE) is supported.

Signature:

responseModalities?: ResponseModality[];

GenerationConfig.responseSchema

Output response schema of the generated candidate text. This value can be a class generated with a Schema static method like Schema.string() or Schema.object() or it can be a plain JS object matching the SchemaRequest interface.
Note: This only applies when the specified responseMimeType supports a schema; currently this is limited to application/json and text/x.enum.

Signature:

responseSchema?: TypedSchema | SchemaRequest;

GenerationConfig.speechConfig

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.

Configuration for speech synthesis for text-to-speech (TTS) models.

Signature:

speechConfig?: SpeechConfig;

GenerationConfig.stopSequences

Signature:

stopSequences?: string[];

GenerationConfig.temperature

Not supported in Gemini 3.x and later models. The model will ignore this parameter if it's included in a request. Omit this parameter and let the model manage sampling automatically.

Signature:

temperature?: number;

GenerationConfig.thinkingConfig

Configuration for "thinking" behavior of compatible Gemini models.

Signature:

thinkingConfig?: ThinkingConfig;

GenerationConfig.topK

Not supported in Gemini 3.x and later models. The model will ignore this parameter if it's included in a request. Omit this parameter and let the model manage sampling automatically.

Signature:

topK?: number;

GenerationConfig.topP

Not supported in Gemini 3.x and later models. The model will ignore this parameter if it's included in a request. Omit this parameter and let the model manage sampling automatically.

Signature:

topP?: number;