Skip to main content
Welcome to the InferenceLab API documentation. This guide will help you get started with integrating the InferenceLab API into your applications.
The InferenceLab API is a RESTful service with predictable, resource-oriented URLs. It utilizes standard HTTP verbs and response codes, and communicates using JSON for both request and response bodies.

Authentication

Keep your API key secure!Do not share it with others or expose it in any client-side code (browsers, apps). Production requests must be routed through your own backend server where your API key can be securely loaded from an environment variable or key management service.
All API endpoints are authenticated using API keys picked up from the Authorization HTTP header as follows:

API endpoints

You can learn more about each API endpoint via the sidebar links. Include your API key in the Authorization header of each request:

Getting Started

  1. Sign Up: Create an account on InferenceLab and retrieve your API key.
  2. Integrate: Use the /model-select endpoint to get model recommendations.
  3. Implement: After receiving a recommendation, integrate with the recommended LLM using your preferred method or via our SDK.

Support

If you have any questions or need assistance, please contact our support team at support@inferencelab.co.