Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions fern/docs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -290,6 +290,9 @@ navigation:
- page: Tool Calling
path: pages/07-llm-gateway/tool-calling.mdx
slug: /tool-calling
- page: Structured Outputs
path: pages/07-llm-gateway/structured-outputs.mdx
slug: /structured-outputs
- page: Migration from LeMUR
path: pages/07-llm-gateway/migration-from-lemur.mdx
slug: /migration-from-lemur
Expand Down
303 changes: 303 additions & 0 deletions fern/pages/07-llm-gateway/structured-outputs.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,303 @@
---
title: "Structured Outputs"
description: "Constrain model responses to follow a specific JSON schema for reliable, parseable outputs"
hidden: true
---

## Overview

Structured outputs allow you to constrain the model's response to follow a specific JSON schema. This ensures the model returns data in a predictable format that can be reliably parsed and processed by your application.

<Note>
Structured outputs are supported by OpenAI (GPT-4.1, GPT-5.x) and Gemini models. Claude and gpt-oss models do not currently support structured outputs.
</Note>

## Getting started

To use structured outputs, include the `response_format` parameter in your request with a `json_schema` type:

<Tabs>
<Tab title="Python" language="python">

```python
import requests

headers = {
"authorization": "<YOUR_API_KEY>",
"content-type": "application/json"
}

response = requests.post(
"https://llm-gateway.assemblyai.com/v1/chat/completions",
headers=headers,
json={
"model": "gemini-2.5-flash-lite",
"messages": [
{
"role": "system",
"content": "You are a helpful math tutor. Guide the user through the solution step by step."
},
{
"role": "user",
"content": "how can I solve 8x + 7 = -23"
}
],
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "math_reasoning",
"schema": {
"type": "object",
"properties": {
"steps": {
"type": "array",
"items": {
"type": "object",
"properties": {
"explanation": {"type": "string"},
"output": {"type": "string"}
},
"required": ["explanation", "output"],
"additionalProperties": False
}
},
"final_answer": {"type": "string"}
},
"required": ["steps", "final_answer"],
"additionalProperties": False
},
"strict": True
}
}
}
)

result = response.json()
print(result["choices"][0]["message"]["content"])
```

</Tab>
<Tab title="JavaScript" language="javascript">

```javascript
const response = await fetch(
"https://llm-gateway.assemblyai.com/v1/chat/completions",
{
method: "POST",
headers: {
authorization: "<YOUR_API_KEY>",
"content-type": "application/json",
},
body: JSON.stringify({
model: "gemini-2.5-flash-lite",
messages: [
{
role: "system",
content:
"You are a helpful math tutor. Guide the user through the solution step by step.",
},
{
role: "user",
content: "how can I solve 8x + 7 = -23",
},
],
response_format: {
type: "json_schema",
json_schema: {
name: "math_reasoning",
schema: {
type: "object",
properties: {
steps: {
type: "array",
items: {
type: "object",
properties: {
explanation: { type: "string" },
output: { type: "string" },
},
required: ["explanation", "output"],
additionalProperties: false,
},
},
final_answer: { type: "string" },
},
required: ["steps", "final_answer"],
additionalProperties: false,
},
strict: true,
},
},
}),
}
);

const result = await response.json();
console.log(result.choices[0].message.content);
```

</Tab>
<Tab title="cURL" language="bash">

```bash
curl -X POST "https://llm-gateway.assemblyai.com/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: <YOUR_API_KEY>" \
-d '{
"model": "gemini-2.5-flash-lite",
"messages": [
{
"role": "system",
"content": "You are a helpful math tutor. Guide the user through the solution step by step."
},
{
"role": "user",
"content": "how can I solve 8x + 7 = -23"
}
],
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "math_reasoning",
"schema": {
"type": "object",
"properties": {
"steps": {
"type": "array",
"items": {
"type": "object",
"properties": {
"explanation": { "type": "string" },
"output": { "type": "string" }
},
"required": ["explanation", "output"],
"additionalProperties": false
}
},
"final_answer": { "type": "string" }
},
"required": ["steps", "final_answer"],
"additionalProperties": false
},
"strict": true
}
}
}'
```

</Tab>
</Tabs>

## Example response

When using structured outputs, the model's response will be a JSON string that conforms to your schema:

```json
{
"request_id": "abc123",
"choices": [
{
"message": {
"role": "assistant",
"content": "{\"steps\":[{\"explanation\":\"Start with the equation 8x + 7 = -23\",\"output\":\"8x + 7 = -23\"},{\"explanation\":\"Subtract 7 from both sides to isolate the term with x\",\"output\":\"8x = -30\"},{\"explanation\":\"Divide both sides by 8 to solve for x\",\"output\":\"x = -30/8 = -15/4 = -3.75\"}],\"final_answer\":\"x = -3.75\"}"
},
"finish_reason": "stop"
}
],
"usage": {
"input_tokens": 85,
"output_tokens": 120,
"total_tokens": 205
}
}
```

You can parse the content as JSON in your application:

```python
import json

content = result["choices"][0]["message"]["content"]
parsed = json.loads(content)

for step in parsed["steps"]:
print(f"{step['explanation']}: {step['output']}")

print(f"Final answer: {parsed['final_answer']}")
```

## Supported models

Structured outputs are supported by the following model families:

| Provider | Supported |
| -------- | --------- |
| OpenAI (GPT-4.1, GPT-5.x) | Yes |
| Gemini | Yes |
| gpt-oss | No |
| Claude | No |

## API reference

### Request parameters

The `response_format` parameter controls how the model formats its response:

| Key | Type | Required? | Description |
| -------------------------- | ------- | --------- | ----------------------------------------------------------------------------------------------- |
| `response_format` | object | No | Specifies the format of the model's response. |
| `response_format.type` | string | Yes | The type of response format. Use `"json_schema"` for structured outputs. |
| `response_format.json_schema` | object | Yes | The JSON schema configuration object. |

### JSON schema object

Check warning on line 252 in fern/pages/07-llm-gateway/structured-outputs.mdx

View workflow job for this annotation

GitHub Actions / lint

[vale] reported by reviewdog 🐶 [AssemblyAI.Headings] Use sentence-style capitalization for 'JSON schema object'. Raw Output: {"message": "[AssemblyAI.Headings] Use sentence-style capitalization for 'JSON schema object'. ", "location": {"path": "fern/pages/07-llm-gateway/structured-outputs.mdx", "range": {"start": {"line": 252, "column": 5}}}, "severity": "WARNING"}

| Key | Type | Required? | Description |
| -------------------------------- | ------- | --------- | ----------------------------------------------------------------------------------------------- |
| `json_schema.name` | string | Yes | A name for the schema. Used for identification purposes. |
| `json_schema.schema` | object | Yes | A valid JSON Schema object that defines the structure of the expected response. |
| `json_schema.strict` | boolean | No | When `true`, the model will strictly adhere to the schema. Recommended for reliable parsing. |

### Schema definition

The `schema` object follows the [JSON Schema](https://json-schema.org/) specification. Common properties include:

| Property | Type | Description |
| ---------------------- | ------------- | --------------------------------------------------------------------------- |
| `type` | string | The data type: `"object"`, `"array"`, `"string"`, `"number"`, `"boolean"`. |
| `properties` | object | For objects, defines the properties and their schemas. |
| `items` | object | For arrays, defines the schema for array items. |
| `required` | array | List of required property names. |
| `additionalProperties` | boolean | When `false`, prevents additional properties not defined in the schema. |

## Best practices

When using structured outputs, keep these recommendations in mind:

Set `strict: true` to ensure the model's response strictly adheres to your schema. This is especially important when your application depends on specific fields being present.

Use `additionalProperties: false` at each level of your schema to prevent the model from adding unexpected fields to the response.

Keep your schemas focused and specific. Complex schemas with many nested levels may increase latency and token usage.

Include clear descriptions in your system or user messages to help the model understand what data to extract or generate for each field.

## Error handling

If the model cannot generate a valid response that matches your schema, you may receive an error or a response that doesn't fully conform to the schema. Always validate the parsed JSON against your expected structure:

```python
import json

try:
content = result["choices"][0]["message"]["content"]
parsed = json.loads(content)

# Validate required fields exist
if "steps" not in parsed or "final_answer" not in parsed:
raise ValueError("Missing required fields in response")

except json.JSONDecodeError as e:
print(f"Failed to parse response as JSON: {e}")
except KeyError as e:
print(f"Unexpected response structure: {e}")
```
Loading
Loading