Orq.ai Documentation - AI Gateway & LLM Collaboration Platform

Prompts store all configuration for interacting with a model: system instructions, messages, model selection, and parameters. A Prompt can be reused across Playgrounds, Experiments, Deployments, and Agents.

Use Cases

Standardize AI Behavior Across Teams

Use prompts as shared instructions so every team and application produces consistent, aligned outputs.

Turn AI Use Cases into Reusable Assets

Package prompts as configurable building blocks that can be reused across products, workflows, and experiments.

Control Model Output Without Code Changes

Adjust behavior, tone, and structure by editing prompts instead of modifying application logic.

Scale AI Features Safely

Roll out improvements, A/B test variations, and manage risk through prompt versioning and controlled updates.

Connect AI to Business Context

Embed domain rules, policies, and structured outputs directly into prompts to align AI with business needs.

Create a Prompt

AI Studio
API & SDK

Navigate to a Project

Open a Project and click the + button at the top.

Select Prompt

Choose Prompt from the menu. The Prompt editor opens in AI Studio.

Standalone prompts are stored in the Project and can be reused across Playgrounds, Experiments, Agents, and Deployments.

Create a Prompt using the Create a Prompt API. The payload defines the name, model, messages, parameters, and metadata.

curl --request POST \
     --url https://api.orq.ai/v2/prompts \
     --header 'accept: application/json' \
     --header 'authorization: Bearer ORQ_API_KEY' \
     --header 'content-type: application/json' \
     --data '{
  "prompt_config": {
    "model_parameters": {
      "responseFormat": null,
      "temperature": 1,
      "maxTokens": 256,
      "topP": 0.7,
      "frequencyPenalty": 0,
      "presencePenalty": 0
    },
    "model": "openai/gpt-4o",
    "model_type": "vision",
    "provider": "openai",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant"
      }
    ]
  },
  "display_name": "MyPrompt",
  "path": "Default/Prompts",
  "metadata": {
    "language": "English"
  },
  "description": "Prompt Description"
}'

The response includes the prompt _id needed for future updates or retrieval.

See the full Create a Prompt API reference.

Choose a Model

AI Studio

Select a model from the model picker at the top of the Prompt editor.

A model must be available through the AI Gateway to appear in the picker.

Model Parameters

Temperature

Controls creativity and predictability. Higher values produce more diverse, surprising responses. Lower values produce more predictable output that sticks closely to learned patterns.

Max Tokens

Sets the upper limit on tokens the model can produce in a single output. Prevents excessively long responses while ensuring enough room for a complete answer.

Top K

Narrows the model’s choices to the k most likely tokens at each generation step. Helps refine output to follow particular patterns or meet specific criteria.

Top P

Nucleus sampling. Selects a pool of likely words based on a probability threshold, balancing creativity with coherence.

Frequency Penalty

Discourages the model from reusing the same words or phrases, encouraging richer and more varied language.

Presence Penalty

Discourages repeated topics or ideas rather than specific words. Higher values lead to more creative and diverse responses.

Messages

AI Studio

Select Add Message in the Prompt Template panel to add a message. Messages define the context the model receives before generating a response.

The prompt template used as context for the language model.

Roles

When adding a message, choose a role to define how the model interprets it:

Role	Description	Example
System	A guideline or context for the language model, directing how it should interpret and respond to requests.	”You are an expert botanist. Respond briefly to questions with one-line answers.”
User	An actual query posed by the user.	”Which plants thrive in shady environments?”
Assistant	Responses to user queries by the language model.	”Ferns, Hostas, and Hydrangeas are some plants that thrive in shady environments.”

Variables

AI Studio

Use {{variable_name}} syntax inside a message to declare a dynamic input. All declared inputs appear in the Inputs block at the top-right of the page, where default values can be set for testing.

Insert an input and override its value during generation.

In a Deployment, populate variables through the inputs field when invoking.

Code example showing how to populate input variables through the inputs field when invoking a Deployment.

Prompt Generator

AI Studio

Select the Generate Prompt button next to the Role Selector to open the prompt generation assistant.

The Generate Prompt button located next to the Role Selector in the prompt editor.

Select Copy to copy the generated prompt to the clipboard.
Select Apply to overwrite the current prompt with the generated one.

Image Generation

AI Studio

Image generation models create images from text descriptions. Select a model with an image tag in the model picker.Selecting an Image Generation Model

The image tag identifies models capable of generating images.

Configuring Parameters for Image ModelsImage generation models have different parameters compared to chat models. Parameters vary per model and affect the generated output.

Example parameters for the DALL-E 3 model.

Using Image Generation in PlaygroundUse image models in the Playground like any other model. Generated images appear as regular messages and can be viewed fullscreen.

Example of image generation using Leonardo AI.

Use Cases

Creative Content: Generate artwork, illustrations, and visual content for marketing materials
Product Design: Create mockups and visual prototypes based on descriptions
Content Creation: Generate images for blogs, social media, and presentations
Concept Visualization: Turn abstract ideas into visual representations

Best Practices

Be Specific: Provide detailed descriptions for better results
Style Guidelines: Include artistic style, mood, and visual elements in your prompts
Parameter Tuning: Experiment with model-specific parameters to achieve desired output quality
Iterative Refinement: Use generated images as starting points for further refinement

Vision

AI Studio
API & SDK

Vision models analyze and interpret images. Select a model with a vision tag in the model picker.

The vision label identifies models that can interpret images.

To include an image as input in the Playground, click the image icon at the top-right of the message. Share a link or upload a file to pass to the model.

An example use case using a vision model for insurance claims processing.

Use Cases

Document Processing: Extract text and information from scanned documents and forms
Visual Quality Control: Analyze product images for defects or compliance
Content Moderation: Automatically review images for inappropriate content
Medical Imaging: Analyze medical scans and diagnostic images (with appropriate models)
Insurance Claims: Process damage assessment photos and documentation

Best Practices

Image Quality: Ensure images are clear and well-lit for best analysis results
Specific Questions: Ask focused questions about what you want to extract or understand
Context Provision: Provide context about what the image represents for better interpretation
Multiple Angles: For complex analysis, consider providing multiple views of the same subject

Pass images to a vision-capable model via a Deployment invocation using the image_url content type with a URL or base64-encoded data URI.

curl --request POST \
     --url https://api.orq.ai/v2/deployments/invoke \
     --header 'accept: application/json' \
     --header 'content-type: application/json' \
     --data '
{
  "messages": [
    {
      "role": "user",
      "content": "describe what you see in this image"
    },
    {
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "Either a URL of the image or the base64 encoded image data."
          }
        }
      ]
    }
  ]
}
'

See the full Invoke API reference.

Fetch a Prompt

API & SDK

Retrieve a Prompt by its ID using the Retrieve a Prompt API.

curl --request GET \
     --url https://api.orq.ai/v2/prompts/PROMPT_ID \
     --header 'accept: application/json' \
     --header 'authorization: Bearer ORQ_API_KEY'

See the full Retrieve a Prompt API reference.

Using Skills

Reference Skills with {{skill.key}} syntax. Inject reusable templates into prompts for modular LLM configuration and DRY prompt engineering.

Using a Skill to enrich a configured prompt.

​Use Cases

​Create a Prompt

​Choose a Model

​Model Parameters

​Messages

​Roles

​Variables

​Prompt Generator

​Image Generation

​Vision

​Fetch a Prompt

​Using Skills

Use Cases

Create a Prompt

Choose a Model

Model Parameters

Messages

Roles

Variables

Prompt Generator

Image Generation

Vision

Fetch a Prompt

Using Skills