Access powerful AI models through a simple OpenAI-compatible API. Pay per token or subscribe for included usage.
Drop-in replacement. Works with any OpenAI SDK or client.
Real-time streaming responses for interactive applications.
Pay per token or subscribe for included usage with rate limits.
Create multiple keys, track usage, rotate anytime.
Monitor usage, costs, and performance in real-time.
Built-in rate limiting and input validation for safety.
Most capable model. $5 / $25 per 1M tokens (input/output).
Premium reasoning model. $5 / $25 per 1M tokens.
Direct Claude access. $5 / $25 per 1M tokens.
Fast & affordable. $3 / $15 per 1M tokens.
curl https://cutazo.com/v1/chat/completions \
-H "Authorization: Bearer cz-your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "cuta-sonnet",
"messages": [{"role": "user", "content": "Hello!"}],
"max_tokens": 1024
}'