API Overview

The Interference API is strictly OpenAI-compatible. All user-facing routes operate under the unified base URL:

https://api.interference.dev/v1

(Or https://interference.designrade.com/v1)

Endpoint Classification

Endpoints are divided into Public (Unauthenticated) and Authenticated (Secured) surfaces:

1. Public Endpoints (No API Key Required)

These endpoints allow discovery and pre-flight configuration without needing an account or credentials:

2. Authenticated Endpoints (API Key Required)

Inference endpoints require an active account, sufficient credit balance, and an Authorization header containing your live API key (sk_live_...):

Authentication

Every authenticated request must include your secret API key in the Authorization header using Bearer authentication:

Authorization: Bearer sk_live_YOUR_API_KEY

• Keys begin with the prefix sk_live_.
• Never commit your API key to public repositories.
• Only create and revoke keys via your secure Interference Console.

Rate Limits & Concurrency

To ensure stability and protect against abusive traffic:

1. Edge IP Rate Limit: An in-memory sliding-window limit of 60 requests per minute per IP is enforced before upstream processing. Exceeding this limit returns HTTP 429 Too Many Requests with a Retry-After header.
2. Per-Key Concurrency: Accounts with active credit balances are granted high concurrent stream capabilities.
3. Response Headers:
   • X-RateLimit-Limit: Maximum requests per minute allowed (e.g. 60).
   • X-RateLimit-Remaining: Estimated remaining requests in the current window.
   • Retry-After: Seconds to wait before retrying when throttled.

HTTP Status Codes

Error Response Format

All errors return standard OpenAI-compatible JSON:

{
  "error": {
    "message": "Missing or malformed API key. Expected 'Authorization: Bearer sk_live_...'",
    "type": "authentication_error",
    "param": null,
    "code": null
  }
}