API Overview

Overview

CAVOS Agents provides an OpenRouter-style API proxy for accessing AI models. Authenticate with sk_live_* API keys and use familiar chat completion endpoints.

Base URL

https://cavos.org/api/v1

Authentication

All API requests require a valid API key in the Authorization header:

curl https://cavos.org/api/v1/chat/completions \
  -H "Authorization: Bearer sk_live_abc123..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Available Endpoints

Method	Path	Description
POST	/v1/chat/completions	Chat completions (streaming & non-streaming)
GET	/api/models	List available models
GET	/api/providers	List model providers
GET	/api/keys	List your API keys
POST	/api/keys	Create a new API key

Rate Limits

Rate limits are applied per API key. Default limits are sufficient for most use cases. Contact support for higher limits.

Credits

All API usage is deducted from your credit balance. You must maintain a minimum $0.50 balance to make API requests. See Credits for details.