Set budget on thinking models

POST

https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview-04-17:generateContent

The thinkingBudget parameter gives the model guidance on the number of thinking tokens it can use when generating a response. A greater number of tokens is typically associated with more detailed thinking, which is needed for solving more complex tasks. thinkingBudget must be an integer in the range 0 to 24576. Setting the thinking budget to 0 disables thinking.

Depending on the prompt, the model might overflow or underflow the token budget.

Request Example

Shell

JavaScript

Java

Swift

curl --location -g --request POST 'https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview-04-17:generateContent?key=' \
--header 'Content-Type: application/json' \
--data-raw '{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain the Occam\s'

Response Example

{}

Request

Query Params

key

string

required

Example:

Header Params

Content-Type

string

required

Example:

application/json

Body Params text/plain

Examples

Responses

🟢200成功

application/json

Body

object {0}

Modified at 2025-04-24 09:55:28

Use thinking models

Function Calling with the Gemini API