API Documentation — Hyperleap AI Help Center

API Overview

Hyperleap provides REST APIs for integrating AI capabilities into your own applications. The APIs support both synchronous and streaming responses.

Full API Reference

Complete API documentation with request/response examples, authentication guides, and more.

View API Documentation

Available APIs

Prompts API

Run AI prompts programmatically with streaming support.

Overview Run Prompt (Non-streaming)Run Prompt (Streaming)

Conversations API

Manage chat conversations with personas and context.

Overview Create Conversation Continue Chat

Feedback & Audit

Track usage and collect feedback on AI interactions.

Capture Feedback Audit Reports

Moderations

Content moderation and safety checks.

Moderations Check

Getting Started with APIs

1. Get Your API Key

Navigate to API Console in your Hyperleap dashboard to generate an API key. Keep this key secure and never expose it in client-side code.

2. Authentication

All API requests require authentication via Bearer token:

Authorization: Bearer YOUR_API_KEY

3. Make Your First Request

Example: Run a prompt synchronously

curl -X POST https://api.hyperleap.ai/prompt-runs/run-sync \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "promptId": "your-prompt-id",
    "replacements": {
      "query": "Hello, world!"
    }
  }'

Tip:

Use streaming endpoints (/async or /run-sse) for better user experience in real-time applications.

API Features

Streaming Support

HTTP/2 Streaming — For server-to-server communication
Server-Sent Events (SSE) — For web browser clients

Rate Limiting

API requests are rate limited based on your plan. Check response headers for rate limit information.

Error Handling

The API returns standard HTTP status codes and JSON error responses. See the Errors documentation for details.

Resources

Need Help?

For API support, contact us at support@hyperleap.ai or join our developer community.