> ## Documentation Index
> Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# ReasoningConfig

## Fields

| Field        | Type                                                                                                    | Required             | Description                                                                                                                                                                                                                                                          | Example    |
| ------------ | ------------------------------------------------------------------------------------------------------- | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- |
| `context`    | [OptionalNullable\[components.ReasoningContext\]](../components/reasoningcontext.mdx)                   | :heavy\_minus\_sign: | Controls which reasoning is available to the model. `auto` uses the model default (same as omitting); `all_turns` includes reasoning from earlier turns passed in input; `current_turn` limits to the current turn only. Only supported by OpenAI GPT-5.6 and newer. | all\_turns |
| `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                                                                                                                                                                                                                                                                  |            |