> ## 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.

# ChatRequestReasoning

Configuration options for reasoning models

## Example Usage

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

let value: ChatRequestReasoning = {};
```

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `context` | [models.ReasoningContext](../models/reasoningcontext.mdx) | ➖ | 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.ChatRequestEffort](../models/chatrequesteffort.mdx) | ➖ | Constrains effort on reasoning for reasoning models | medium |
| `enabled` | *boolean* | ➖ | Enables reasoning with default settings. Defaults to being inferred from `effort` or `max_tokens`. | true |
| `exclude` | *boolean* | ➖ | When true, the model still reasons but the reasoning is omitted from the response. Defaults to false. | false |
| `maxTokens` | *number* | ➖ | Maximum number of tokens the model may spend on reasoning, for models that take a reasoning token budget instead of an effort level. Cannot be combined with `reasoning.effort` or the top-level `reasoning_effort`: a request that sets both is rejected with "Only one of "reasoning.effort" and "reasoning.max\_tokens" can be specified". | 2000 |
| `mode` | [models.ReasoningMode](../models/reasoningmode.mdx) | ➖ | 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.ChatReasoningSummaryVerbosityEnum](../models/chatreasoningsummaryverbosityenum.mdx) | ➖ | N/A | concise |