​

Meibel API

Welcome to the Meibel AI API reference documentation. Our API allows you to interact with all our services programmatically, giving you full control over runtime execution, confidence scoring, and adaptive workflows.

​

Overview

The Meibel API enables developers to:

• Create and manage datasources and dataelements for contextual retrieval
• Run chat completions with runtime control and confidence scoring
• Stream responses from our AI models
• Build experiences with adaptive workflows

​

Authentication

All API requests require authentication using an API key. Your API key carries many privileges, so be sure to keep it secure. Don’t share your API key in publicly accessible areas such as GitHub, client-side code, or in your applications.

# Example request with authentication
curl -X GET https://api.meibel.ai/v1/datasources \
  -H "Authorization: Bearer YOUR_API_KEY"

​

Rate Limits

The Meibel AI API implements rate limiting to ensure fair usage across all users. Rate limits vary by endpoint and are specified in the HTTP headers of API responses:

• X-RateLimit-Limit: The maximum number of requests you’re permitted to make per time period
• X-RateLimit-Remaining: The number of requests remaining in the current rate limit window
• X-RateLimit-Reset: The time at which the current rate limit window resets (UTC epoch seconds)

If you exceed the rate limit, an error response returns with status code 429 (Too Many Requests).

​

SDK Support

We provide official SDKs to make integration with our API even easier:

​

Getting Started

To start using the Meibel AI API:

​

Need help?

If you encounter any issues, you can:

• Check our developer guides
• Email our support team at support@meibel.ai
• Open an issue on GitHub