---
title: Reasoning
description: Extended thinking for supported models
---

## Overview

Models that support reasoning can "think" before answering, producing higher-quality responses for complex questions. When a reasoning-capable model is available, ChatJS automatically creates two variants in the model selector so you can toggle reasoning on or off per conversation.

## How it works

### Automatic model splitting

When a model is tagged with `reasoning` by the gateway, ChatJS creates two entries in the model selector:

| Variant   | Model ID                 | Behavior                  |
| --------- | ------------------------ | ------------------------- |
| Reasoning | `openai/gpt-5-reasoning` | Extended thinking enabled |
| Standard  | `openai/gpt-5`           | No extended thinking      |

Both variants point to the same underlying API model. The `-reasoning` suffix controls whether reasoning options are sent with the request.

### UI

When a model responds with reasoning content, the UI renders a collapsible "Thinking" section above the answer. You can expand it to inspect the model's chain of thought.

While the model is still generating, the reasoning section streams in real time.

### Cross-model compatibility

Reasoning parts are automatically stripped from message history before sending to the LLM. This prevents errors when a user switches between a reasoning and non-reasoning model mid-conversation.

## Supported providers

Each provider activates reasoning differently. ChatJS handles this automatically based on the model's `owned_by` field.

| Provider | Mechanism | Notes |
| --- | --- | --- |
| OpenAI | `reasoningSummary` provider option | gpt-5 family uses `reasoningEffort: "low"` |
| Anthropic | `thinking` provider option | Budget of 4096 tokens |
| Google | `thinkingConfig` provider option | Budget of 10,000 tokens |
| xAI | `extractReasoningMiddleware` | Parses `<think>` tags from the response |

## Customization

### Adjusting reasoning budgets

The defaults live in `packages/gateways/src/provider-options.ts` in the ChatJS repository. In a generated app, customize the returned options in `lib/ai/providers.ts`, after calling the shared `getModelProviderOptions` helper. Override the nested provider budget you want to change:

```ts
// Anthropic thinking budget
anthropic: {
  thinking: {
    type: "enabled",
    budgetTokens: 4096, // Increase for deeper reasoning
  },
}

// Google thinking budget
google: {
  thinkingConfig: {
    thinkingBudget: 10_000, // Increase for deeper reasoning
  },
}
```

### Disabling reasoning variants

To hide reasoning variants for a specific model, add the base model ID to `disabledModels` in `chat.config.ts`. The reasoning variant is derived from the base model, so disabling the base model removes both variants.

To disable reasoning globally, you would need to modify `buildAppModels` in `lib/ai/app-models.ts` to skip the reasoning branch.