> ## 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

## Example Usage

```typescript theme={null}
import { ReasoningConfig } from "@openrouter/sdk/models";

let value: ReasoningConfig = {};
```

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `context` | [models.ReasoningContext](../models/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` | [models.ReasoningEffort](../models/reasoningeffort.mdx) | :heavy\_minus\_sign: | N/A | medium |
| `mode` | [models.ReasoningMode](../models/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` | [models.ReasoningSummaryVerbosity](../models/reasoningsummaryverbosity.mdx) | :heavy\_minus\_sign: | N/A | auto |
| `enabled` | *boolean* | :heavy\_minus\_sign: | N/A | |
| `maxTokens` | *number* | :heavy\_minus\_sign: | N/A | |