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

# Structured Output

> Get JSON back instead of prose

Asking a model for JSON in a system prompt works most of the time, which is the problem.
`generateStructured` validates the result against a schema and can repair it.

```swift theme={null}
let result = try await RunAnywhere.llm.generateStructured(
    prompt: "Extract the name and age: Dana is 34.",
    schema: schema,
    mode: .validationOnly,
    options: LlmOptions(temperature: 0.1)
)
```

## Enforcement modes

| Mode              | Behaviour                                            |
| ----------------- | ---------------------------------------------------- |
| `.validationOnly` | Generate freely, then validate. The default.         |
| `.repair`         | Validate, then retry once with a repair instruction. |
| `.constrained`    | **Throws today.**                                    |

<Warning>
  Constrained mode **throws** on every SDK. It needs engine-level constrained decoding, which is not
  wired in yet. Use validation-only or repair.
</Warning>

Validation-only is the default and is right when a retry is cheap. Repair costs a second
generation when the first is invalid, which is worth it when the call is user-facing and a
failure means showing an error.

## The schema

```swift theme={null}
let schema = JsonSchema(/* your JSON schema */)
```

Keep schemas small. A small model handles four flat fields reliably and a deeply nested
structure badly. When you need something complex, ask for the pieces separately rather than
one large object.

Naming fields the way a person would helps: `totalPrice` gets better results than `tp`.

## Reading the result

```swift theme={null}
struct Person: Decodable {
    let name: String
    let age: Int
}

let person = try result.decode(Person.self)
```

## When to reach for this

| Task                           | Approach                                |
| ------------------------------ | --------------------------------------- |
| Extracting fields from text    | Structured output                       |
| Classifying into fixed labels  | Structured output, or a one-word prompt |
| Anything you will `JSON.parse` | Structured output                       |
| Prose for a human to read      | Plain generation                        |

If you are about to write a regex over a model's reply, you want this instead.

## Temperature

Lower it. Structured extraction is not a creative task, and `0.1` to `0.3` produces far more
consistent field values than the default.