Version: 0.1.0

ComfyUI API Service

A serverless inference platform for executing ComfyUI workflows.

Overview

This API allows you to submit ComfyUI workflow definitions for GPU-accelerated execution. Jobs are automatically distributed to available GPU nodes with intelligent cache-aware routing to minimize model loading times.

Authentication

All API endpoints (except health checks) require authentication using an API key. Include your API key in the Authorization header:

Authorization: Bearer sk_your_api_key_here

API keys can be obtained from the dashboard. Test keys (prefixed with sk_test_) are available for development.

Rate Limits

Rate limits are applied based on your account tier:

Tier	Requests/min	Concurrent Jobs	Queue Depth
Free	60	2	5
Pro	300	10	50
Enterprise	1000	50	500

Rate limit headers are included in all responses:

• X-RateLimit-Limit: Maximum requests per minute
• X-RateLimit-Remaining: Remaining requests in current window
• X-RateLimit-Reset: Unix timestamp when the rate limit resets

Webhooks

Optionally provide a webhook_url when creating a job to receive notifications when the job completes. Webhook URLs must use HTTPS.

Error Handling

All errors follow a consistent format with an error object containing:

• code: Machine-readable error code
• message: Human-readable description
• request_id: Unique identifier for debugging

Idempotency

For job creation, you can include an idempotency_key to ensure that duplicate requests return the same response. Keys are valid for 24 hours.

Authentication

API Key: ApiKeyAuth

API key authentication. Include your API key in the Authorization header with the format: Bearer sk_...

Security Scheme Type:	apiKey
Header parameter name:	Authorization

Contact

API Support:

License