API Reference

The Curate-Me platform exposes three independent APIs that share the same backend codebase but serve different audiences and use cases.

Base URLs

For local development:

Triple API Architecture

The backend runs as three separate FastAPI applications:

• Gateway API (main_gateway.py, port 8002) — LLM reverse proxy with governance chain (rate limiting, cost control, PII scanning, model allowlists, HITL approvals) and runner management endpoints.
• B2B API (main_b2b.py, port 8001) — Dashboard admin features, agent management, cost tracking, workflow orchestration, and runner configuration.
• B2C API (main_b2c.py, port 8000) — Reference implementation consumer features.

All three applications share the same codebase, database connections, and service layer, but have different route registrations and middleware configurations.

Request Format

All requests and responses use JSON. Set the Content-Type header on all requests that include a body:

Content-Type: application/json

Authentication

All authenticated endpoints require a JWT Bearer token in the Authorization header:

Authorization: Bearer {access_token}

For B2B multi-tenant requests, include the organization context header:

X-Org-ID: {organization_id}

For Gateway requests, use an API key:

X-CM-API-Key: cm_sk_xxx

See the Authentication page for details on obtaining and refreshing tokens.

Rate Limiting

All endpoints are rate-limited. The current limits are returned in the response headers:

When rate-limited, the API returns a 429 Too Many Requests response.

Interactive Documentation

All three APIs expose interactive Swagger UI documentation:

• Gateway: https://api.curate-me.ai/docs 
• B2B: https://api.curate-me.ai/docs 
• B2C: https://api.curate-me.ai/docs 

Pagination

Endpoints that return collections support offset-based pagination:

GET /api/v1/resource?offset=0&limit=20

Paginated responses include metadata:

{
  "items": [...],
  "total": 142,
  "offset": 0,
  "limit": 20
}

Error Format

All errors follow a consistent format:

{
  "error": {
    "code": "RATE_LIMIT_EXCEEDED",
    "message": "You have exceeded the rate limit. Try again in 30 seconds.",
    "details": {
      "retry_after": 30
    }
  }
}

HTTP Status Codes