Install Engines

Install Local Engines

Jan currently doesn't support installing a local engine yet.

Install Remote Engines

Step-by-step Guide

You can add any OpenAI API-compatible providers like OpenAI, Anthropic, or others. To add a new remote engine:

Navigate to Settings () > Engines
At Remote Engine category, click + Install Engine

Install Remote Engines

Fill in the following required information:

Install Remote Engines

Field	Description	Required
Engine Name	Name for your engine (e.g., "OpenAI", "Claude")	✓
API URL	The base URL of the provider's API	✓
API Key	Your authentication key from the provider	✓
Model List URL	URL for fetching available models
API Key Template	Custom authorization header format
Request Format Conversion	Function to convert Jan's request format to provider's format
Response Format Conversion	Function to convert provider's response format to Jan's format

The conversion functions are only needed for providers that don't follow the OpenAI API format. For OpenAI-compatible APIs, you can leave these empty.

For OpenAI-compatible APIs like OpenAI, Anthropic, or Groq, you only need to fill in the required fields. Leave optional fields empty.

Click Install
Once completed, you should see your engine in Engines page:
- You can rename or uninstall your engine
- You can navigate to its own settings page

Install Remote Engines

Examples

OpenAI-Compatible Setup

Here's how to set up OpenAI as a remote engine:

Engine Name: OpenAI
API URL: https://api.openai.com
Model List URL: https://api.openai.com/v1/models
API Key: Your OpenAI API key
Leave other fields as default

Custom APIs Setup

If you're integrating an API that doesn't follow OpenAI's format, you'll need to use the conversion functions. Let's say you have a custom API with this format:


// Custom API Request Format
{
  "prompt": "What is AI?",
  "max_length": 100,
  "temperature": 0.7
}
// Custom API Response Format
{
  "generated_text": "AI is...",
  "tokens_used": 50,
  "status": "success"
}

Here's how to set it up in Jan:


Engine Name: Custom LLM
API Key: your_api_key_here
Header template: your header template here
Transform request template: your transform request template here
Transform response template: your transform response template here

Header template


"Authorization: Bearer {{api_key}}"

Transform request template: Convert from Jan's OpenAI-style format to your API's format


"chat_completions": {
  "url": "https://api.custom_endpoint.com/v1/messages",
  "template": "{
{% for key, value in input_request %}
  {% if key == "messages" %} 
    "prompt": "{{ last(input_request.messages).content }}"
  {% else if key == "max_tokens" or key == "temperature" %}
    "{{ key }}": {{ tojson(value) }}  
  {% endif %}
{% endfor %}
}"
}

Transform response template Convert from your API's format back to OpenAI-style format


"chat_completions": {
"template": "{
{
  "choices": [{
      "message": {
        "role": "assistant",
        "content": "{{ input_request.generated_text }}"
      }
    }],
    "usage": {
      "total_tokens": {{ input_request.tokens_used }}
    }
}
}"
}

Expected Formats:

Jan's Request Format


{
  "messages": [
    {"role": "user", "content": "What is AI?"}
  ],
  "max_tokens": 100,
  "temperature": 0.7
}

Jan's Expected Response Format


{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "AI is..."
    }
  }],
  "usage": {
    "total_tokens": 50
  }
}

⚠️

Make sure to test your conversion functions thoroughly. Incorrect conversions may cause errors or unexpected behavior.

OpenRouter Overview