Output Schema - Endprompt

The output schema defines what your endpoint returns. While optional, defining an output schema ensures consistent responses and enables validation of LLM outputs.

Why Define Output Schema?

Consistent Responses

Ensure every response follows the same structure

Documentation

OpenAPI docs show exactly what callers receive

Validation

Catch malformed LLM responses before they reach your app

Type Safety

Frontend/backend code can rely on specific fields

Adding Output Fields

Navigate to your endpoint’s Output Schema tab and click Add Field.

Field Configuration

Property	Required	Description
Name	Yes	Field name in the response JSON
Type	Yes	Data type (string, number, boolean, array, object)
Description	No	What this field contains

Output fields are never “required” in the traditional sense—they define what the LLM should return. If the LLM doesn’t include a field, it will be omitted from the response.

Field Types

Output schemas support the same types as input schemas:

{
  "name": "summary",
  "type": "string",
  "description": "The summarized content"
}

{
  "name": "confidence",
  "type": "number",
  "description": "Confidence score between 0 and 1"
}

{
  "name": "is_spam",
  "type": "boolean",
  "description": "Whether the content is spam"
}

{
  "name": "keywords",
  "type": "array",
  "items": { "type": "string" },
  "description": "Extracted keywords"
}

{
  "name": "metadata",
  "type": "object",
  "properties": {
    "word_count": { "type": "integer" },
    "language": { "type": "string" }
  }
}

Adding an image output field signals that this endpoint generates images. When present, the rendered prompt is sent to the model’s image generation API — no JSON output instructions are appended.

{
  "name": "generated_image",
  "type": "image",
  "description": "The generated product image"
}

Configuring generation defaults:Use the Example Value field on the image output to store default generation config as JSON:

{
  "size": "1024x1024",
  "quality": "high"
}

These defaults can be overridden per-prompt using the Custom Parameters panel. See Image Generation & Vision for the full configuration guide.

Generation parameters (size, quality, background, etc.) are model/provider-specific. Check your provider’s API docs for supported values.

Prompting for Structured Output

Your prompt must instruct the LLM to return JSON matching your schema. Here’s the pattern:

Analyze the following text for sentiment:

{{ inputs.text }}

Respond with a JSON object containing:
- sentiment: "positive", "negative", or "neutral"
- confidence: a number between 0 and 1
- keywords: an array of key terms that influenced the analysis

Return only valid JSON, no additional text.

If your prompt doesn’t ask for JSON output, the LLM may return plain text that won’t parse correctly.

Example Schemas

Sentiment Analysis

Output Schema:

{
  "type": "object",
  "properties": {
    "sentiment": {
      "type": "string",
      "description": "Overall sentiment"
    },
    "confidence": {
      "type": "number",
      "description": "Confidence score 0-1"
    },
    "aspects": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "aspect": { "type": "string" },
          "sentiment": { "type": "string" }
        }
      },
      "description": "Sentiment by aspect"
    }
  }
}

Example Response:

{
  "sentiment": "positive",
  "confidence": 0.92,
  "aspects": [
    { "aspect": "price", "sentiment": "neutral" },
    { "aspect": "quality", "sentiment": "positive" },
    { "aspect": "delivery", "sentiment": "positive" }
  ]
}

Content Classification

Output Schema:

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Primary category"
    },
    "subcategories": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Secondary categories"
    },
    "confidence_scores": {
      "type": "object",
      "description": "Confidence per category"
    }
  }
}

Text Extraction

Output Schema:

{
  "type": "object",
  "properties": {
    "entities": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "text": { "type": "string" },
          "type": { "type": "string" },
          "start": { "type": "integer" },
          "end": { "type": "integer" }
        }
      }
    },
    "summary": {
      "type": "string"
    }
  }
}

Response Validation

When an output schema is defined, Endprompt:

Parses the LLM response as JSON
Validates against your schema
Returns the validated response

If validation fails, you’ll see details in the execution logs.

Start without an output schema while experimenting, then add one once you’ve stabilized the prompt’s output format.

JSON Schema Preview

The Output Schema tab shows the complete JSON Schema:

{
  "type": "object",
  "properties": {
    "summary": {
      "type": "string",
      "description": "Concise summary of the content"
    },
    "bullet_points": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Key points as bullet list"
    },
    "word_count": {
      "type": "integer",
      "description": "Number of words in summary"
    }
  }
}

Best Practices

Keep schemas simple

Flat structures are easier for LLMs to produce consistently than deeply nested ones.

Be explicit in prompts

Tell the LLM exactly what JSON structure you expect, including field names.

Use descriptive field names

Field names like is_spam are clearer than spam or s.

Document everything

Add descriptions to every field—they appear in your OpenAPI docs.

Test edge cases

Test with unusual inputs to see if the LLM still produces valid JSON.

Without Output Schema

If you don’t define an output schema:

The raw LLM response is returned
No JSON parsing or validation occurs
The response may be plain text or unstructured

This is fine for simple use cases where you just need text back.

Next Steps

Create a Prompt

Write prompts that produce structured output

Test Your Endpoint

Verify your schema works with real requests

​Why Define Output Schema?

Consistent Responses

Documentation

Validation

Type Safety

​Adding Output Fields

​Field Configuration

​Field Types

​Prompting for Structured Output

​Example Schemas

​Sentiment Analysis

​Content Classification

​Text Extraction

​Response Validation

​JSON Schema Preview

​Best Practices

​Without Output Schema

​Next Steps

Create a Prompt

Test Your Endpoint

Why Define Output Schema?

Adding Output Fields

Field Configuration

Field Types

Prompting for Structured Output

Example Schemas

Sentiment Analysis

Content Classification

Text Extraction

Response Validation

JSON Schema Preview

Best Practices

Without Output Schema

Next Steps