Skip to main content

​
Introduction

Jan provides a built-in, OpenAI-compatible API server that runs entirely on your computer, powered by llama.cpp. Use it as a drop-in replacement for cloud APIs to build private, offline-capable AI applications. The API server is accessible at http://127.0.0.1:1337 by default and follows OpenAI’s API conventions.

​
Base URL

http://127.0.0.1:1337/v1

​
Authentication

All API requests require authentication using a Bearer token in the Authorization header.

​
Setting up Authentication

  1. Navigate to Settings > Local API Server in Jan
  2. Enter a custom API Key (e.g., secret-key-123)
  3. Click Start Server

​
Using the API Key

Include the API key in all requests: 
Authorization: Bearer YOUR_API_KEY

​
Example Request

curl http://127.0.0.1:1337/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer secret-key-123" \
  -d '{
    "model": "llama3-8b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

​
Server Configuration

​
Network Settings

​
host
string
default:"127.0.0.1"
The network address the server listens on.
  • 127.0.0.1: Accessible only from your computer (most secure)
  • 0.0.0.0: Accessible from other devices on your network
​
port
number
default:"1337"
The port number for the API server. You can change this to any available port (e.g., 8000).
​
api_prefix
string
default:"/v1"
The base path for all API endpoints. Follows OpenAI’s convention.

​
Security Settings

​
api_key
string
required
A mandatory secret key to authenticate requests. Must be included in the Authorization: Bearer YOUR_API_KEY header for all requests.
​
trusted_hosts
string
A comma-separated list of hostnames allowed to access the server. Provides an additional layer of security when the server is exposed on your network.

​
Advanced Settings

​
cors
boolean
default:true
Enables Cross-Origin Resource Sharing (CORS) to allow web applications running on different domains to make requests to the API server. Disable for non-browser-based applications.
​
verbose_logs
boolean
default:true
Provides detailed, real-time logs of all incoming requests, responses, and server activity. Useful for debugging.

​
Available Endpoints

Chat Completions

Generate chat completions with streaming support

Models

List and retrieve available models

Embeddings

Generate embeddings for text inputs

​
Error Handling

The API uses standard HTTP status codes:
  • 200 - Success
  • 400 - Bad Request (invalid parameters)
  • 401 - Unauthorized (missing or invalid API key)
  • 404 - Not Found (model not available)
  • 500 - Internal Server Error

​
Error Response Format

{
  "error": {
    "message": "Error description",
    "type": "invalid_request_error",
    "code": "model_not_found"
  }
}

​
Troubleshooting

​
Connection Refused

The server is not running, or your application is pointing to the wrong host or port.

​
401 Unauthorized

Your API Key is missing from the Authorization header or is incorrect.

​
404 Not Found

  • The model ID in your request body does not match an available model in Jan
  • Your request URL is incorrect (check the API Prefix)

​
CORS Error (in web browser)

Ensure the CORS toggle is enabled in Jan’s settings.

​
Out of Context

The conversation has exceeded the model’s context window. The API will return a finish_reason of length.

Build docs developers (and LLMs) love

Get started for freeTalk to us