Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.endprompt.ai/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks you through creating a new prompt for your endpoint.

​
Prerequisites

Before creating a prompt, ensure you have:
  • An endpoint created
  • Input schema defined (so you know what data you’ll receive)
  • Output schema defined (optional, but recommended)

​
Creating a Prompt

1

Navigate to the Endpoint

Open the endpoint you want to add a prompt to.
2

Go to Prompts Tab

Click the Prompts tab in the endpoint workspace.
3

Click Create Prompt

Click the Create Prompt button.
4

Configure Basic Settings

Fill in the prompt details:
FieldDescription
NameDescriptive name (e.g., “Detailed Summary v2”)
ModelSelect the LLM to use
TemperatureRandomness (0.0 - 1.0)
Max TokensMaximum response length
5

Write the Template

Enter your prompt template using Liquid syntax.
6

Save

Click Save to create the prompt as a Draft.

​
Prompt Settings Explained

​
Model Selection

Choose from available models:
ProviderModelsBest For
OpenAIGPT-4o, GPT-4, GPT-3.5-turboGeneral purpose, coding, analysis
OpenAIgpt-image-1Image generation and editing
AnthropicClaude 3 Opus, Sonnet, HaikuLong context, nuanced responses
GoogleGemini 2.0 Flash, Gemini 2.5 ProFast multimodal, vision
Start with GPT-4o or Claude 3 Sonnet for the best balance of quality and speed. For image generation, use gpt-image-1.
Select an image generation model when your endpoint has image output fields. Select a vision model (GPT-4o, Claude 3, Gemini) when your endpoint has image inputs with text/JSON outputs.

​
Temperature

Controls randomness in responses:
ValueBehaviorUse Case
0.0 - 0.3Deterministic, consistentClassification, extraction, facts
0.4 - 0.6BalancedGeneral tasks, summarization
0.7 - 1.0Creative, variedCreative writing, brainstorming

​
Max Tokens

Maximum tokens in the response:
  • Short responses (100-500): Classifications, extractions
  • Medium responses (500-2000): Summaries, analyses
  • Long responses (2000+): Detailed reports, long-form content
Higher max tokens = higher costs. Set appropriate limits for your use case.

​
Custom Parameters for Image Generation

When using an image generation model, use the Custom Parameters panel to configure provider-specific options like size, quality, and background. Custom Parameters are defined as a JSON array of name/value pairs: 
[
  { "name": "size", "value": "1024x1536" },
  { "name": "quality", "value": "high" },
  { "name": "background", "value": "transparent" }
]
Parameter precedence: Hardcoded defaults → Output Field Example Value → Custom Parameters
These parameters are model/provider-specific. Check your provider’s API documentation for supported values. For example, background is an OpenAI-specific parameter.
Image generation prompts don’t need JSON output instructions — the prompt itself is the image description sent to the generation API.
A system-level instruction that sets context: 
You are a professional content editor with 20 years of experience. 
You always provide constructive, actionable feedback.
Not all models support system prompts. When unsupported, it’s prepended to the main prompt.

​
Writing Effective Templates

​
Structure Your Prompt

A well-structured prompt typically includes:
  1. Role/Context — Who is the AI in this scenario
  2. Instructions — What to do, step by step
  3. Input Data — The user’s data to process
  4. Output Format — How to structure the response

​
Example: Complete Prompt

You are an expert content analyst specializing in {{ inputs.industry | default: "general" }} content.

## Your Task
Analyze the provided text and extract key insights.

## Instructions
1. Read the content carefully
2. Identify the {{ inputs.num_insights | default: 3 }} most important insights
3. For each insight, provide:
   - A concise title
   - A brief explanation
   - Relevance score (1-10)

## Content to Analyze
{{ inputs.content | truncate: 10000 }}

{% if inputs.focus_areas %}
## Focus Areas
Pay special attention to:
{% for area in inputs.focus_areas %}
- {{ area }}
{% endfor %}
{% endif %}

## Output Format
Return a JSON object:
{
  "insights": [
    {
      "title": "string",
      "explanation": "string",
      "relevance": number
    }
  ],
  "overall_summary": "string"
}

Return only valid JSON, no additional text.

​
Common Patterns

​
Classification

Classify the following text into one of these categories:
{% for cat in inputs.categories %}
- {{ cat }}
{% endfor %}

Text: {{ inputs.text }}

Return JSON: {"category": "selected", "confidence": 0.0-1.0}

​
Extraction

Extract the following information from the text:
- Names of people
- Dates mentioned
- Key actions or events

Text: {{ inputs.text }}

Return JSON with arrays for each type.

​
Generation

Write a {{ inputs.tone }} {{ inputs.content_type }} about {{ inputs.topic }}.

Requirements:
- Length: approximately {{ inputs.word_count | default: 200 }} words
- Audience: {{ inputs.audience | default: "general" }}
{% if inputs.keywords %}
- Include these keywords: {{ inputs.keywords | join: ", " }}
{% endif %}

​
Transformation

Rewrite the following text to be more {{ inputs.style }}.

Original:
{{ inputs.text }}

Maintain the core meaning while improving {{ inputs.focus }}.

​
Testing Your Prompt

After saving, test immediately:
  1. Click the Test button next to your prompt
  2. Fill in the auto-generated form with sample data
  3. Click Run Test
  4. Review the response
  5. Iterate on your template as needed
Test with edge cases: empty optional fields, very long inputs, unusual values. Your prompt should handle them gracefully.

​
Best Practices

If you need JSON, say so explicitly and provide an example structure.
LLMs follow numbered steps more reliably than prose paragraphs.
Tell the model what NOT to do: “Do not include explanations outside the JSON.”
Few-shot examples dramatically improve consistency for complex tasks.
Use conditionals to handle missing data: {% if inputs.optional_field %}

​
Next Steps

Testing Prompts

Learn to test prompts thoroughly

Prompt Versions

Understand versioning and promotion