Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.keywordsai.co/llms.txt

Use this file to discover all available pages before exploring further.

Thinking mode allows supported models to show their reasoning process before providing the final answer. This feature is currently available for select models like Claude Sonnet 4.

​
Basic Usage

To enable thinking mode, add the thinking parameter to your request: 
payload = {
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 16000,
    "thinking": {
        "type": "enabled",
        "budget_tokens": 10000
    },
    "messages": [
        {
            "role": "user",
            "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?"
        }
    ]
}

​
Parameters

  • type: Set to "enabled" to activate thinking mode
  • budget_tokens: Maximum number of tokens allocated for the thinking process (optional)

​
Supported Models

  • choose models that support thinking like gpt-5, claude-sonnet-4-20250514.

​
Response Format

When thinking is enabled, the response will include additional fields showing the model’s reasoning process. See the Log Thinking documentation for details on the response structure.