diff --git a/source/_integrations/anthropic.markdown b/source/_integrations/anthropic.markdown index cdc18254cdf..3bb8c935176 100644 --- a/source/_integrations/anthropic.markdown +++ b/source/_integrations/anthropic.markdown @@ -67,5 +67,7 @@ Model: Maximum Tokens to Return in Response: description: The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Different models have different maximum values for this parameter. See [models](https://docs.anthropic.com/en/docs/models-overview) for details. Temperature: - description: Amount of randomness injected into the response. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. + description: Amount of randomness injected into the response. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. This parameter is ignored if extended thinking is enabled (see below). +Thinking budget: + description: For models with [extending thinking](https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking) support, such as Claude 3.7 Sonnet, this parameter determines the maximum number of tokens Claude is allowed use for its internal reasoning process. Larger budgets can improve response quality by enabling more thorough analysis for complex problems, although Claude may not use the entire budget allocated, especially at ranges above 32K. Anthropic suggests starting at the minimum and increasing the thinking budget incrementally to find the optimal range for Claude to perform well for your use case. Higher token counts may allow you to achieve more comprehensive and nuanced reasoning, but there may also be diminishing returns depending on the task. Be prepared for potentially longer response times due to the additional processing required for the reasoning process. The value must always be less than the `Maximum Tokens` specified. If the value is below `1024`, then extended thinking is disabled. This parameter is ignored if the model does not support extended thinking. {% endconfiguration_basic %}