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

# Reasoning models

> How Foundry exposes reasoning — when it kicks in, what you see, how you control depth.

Some replies need the model to *think* before it answers. Foundry supports reasoning models (GPT-5 family, newer Grok, others) and gives you two controls:

1. **[Reasoning Effort](/foundry/reasoning/effort-control)** — how deep should the model think?
2. **[Live Reasoning View](/foundry/reasoning/live-view)** — watch the model think in real time.

<Note>
  **Screenshot coming.** Reasoning block above a reply.
</Note>

## When reasoning kicks in

Foundry auto-routes hard problems to reasoning-capable models. You'll see a **collapsible Reasoning block** above the assistant's reply when reasoning is active.

The block stays collapsed by default. Click to expand and see the model's chain of thought as it streams.

## What the block contains

* A **Brain** header with a spinner while thinking.
* A streaming, monospace dump of the model's reasoning trace.
* A finished state once the answer is ready below.

## Cost and time

Reasoning adds tokens and seconds. The deeper the effort, the bigger the bill and the longer the wait. Use [Effort Control](/foundry/reasoning/effort-control) to dial it in.

## Related

<CardGroup cols={2}>
  <Card title="Effort control" icon="sliders" href="/foundry/reasoning/effort-control">
    Low / Medium / High and what they buy you.
  </Card>

  <Card title="Live reasoning view" icon="eye" href="/foundry/reasoning/live-view">
    See the model think.
  </Card>
</CardGroup>