--- title: "ReasoningConfig" --- Configuration for reasoning mode in the response ## Fields | Field | Type | Required | Description | Example | | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `effort` | [OptionalNullable[components.ReasoningEffort]](../components/reasoningeffort.mdx) | :heavy_minus_sign: | N/A | medium | | `mode` | [OptionalNullable[components.ReasoningMode]](../components/reasoningmode.mdx) | :heavy_minus_sign: | Selects the reasoning mode. `standard` is the default; `pro` engages deeper reasoning on models that support it, billed at standard token rates. Only supported by OpenAI GPT-5.6 and newer. | standard | | `summary` | [OptionalNullable[components.ReasoningSummaryVerbosity]](../components/reasoningsummaryverbosity.mdx) | :heavy_minus_sign: | N/A | auto | | `enabled` | *OptionalNullable[bool]* | :heavy_minus_sign: | N/A | | | `max_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | N/A | |