Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window.

GenerationConfig

Generation config.

JSON representation
{ "stopSequences": [ string ], "responseMimeType": string, "temperature": number, "topP": number, "topK": number, "candidateCount": integer, "maxOutputTokens": integer, "presencePenalty": number, "frequencyPenalty": number }

JSON representation

{
  "stopSequences": [
    string
  ],
  "responseMimeType": string,
  "temperature": number,
  "topP": number,
  "topK": number,
  "candidateCount": integer,
  "maxOutputTokens": integer,
  "presencePenalty": number,
  "frequencyPenalty": number
}

Fields
`stopSequences[]`	`string` Optional. Stop sequences.
`responseMimeType`	`string` Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
`temperature`	`number` Optional. Controls the randomness of predictions.
`topP`	`number` Optional. If specified, nucleus sampling will be used.
`topK`	`number` Optional. If specified, top-k sampling will be used.
`candidateCount`	`integer` Optional. Number of candidates to generate.
`maxOutputTokens`	`integer` Optional. The maximum number of output tokens to generate per message.
`presencePenalty`	`number` Optional. Positive penalties.
`frequencyPenalty`	`number` Optional. Frequency penalties.