Quick start
Everything you need to make your first request — sign up, grab a key, set your base URL, and go.
Compatible with OpenAI SDK · Anthropic SDK · cURL
Step 1 — Sign up & get free credit
Step 2 — Create an API key
Step 3 — Set your base URL
https://clauden.ai/v1
https://clauden.ai/v1/anthropic
Step 4 — Send your first request
curl https://clauden.ai/v1/chat/completions \
-H "Authorization: Bearer $CLAUDEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-4-6",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Send your own API key (starts with sk-) in the Authorization header as a Bearer token.
API reference essentials
Authentication
Every request needs an Authorization header with your API key as a Bearer token. Keys are created in the console under API Keys and start with your account prefix. Keep keys server-side; never ship them in client-side code.
Authorization: Bearer $CLAUDEN_API_KEY
Streaming
Both endpoints support server-sent events. Set "stream": true in the request body and read the response line by line; chunks follow the OpenAI delta format on /v1/chat/completions and the Anthropic event format on /v1/anthropic. Remember to handle the final [DONE] line and network timeouts.
Model naming
The model parameter routes your request: claude-* names go to Anthropic, gpt-* to OpenAI, gemini-* to Google. The exact list of enabled model names and per-token prices is always on the pricing page — use those strings verbatim.
Error codes
| HTTP | Type |
|---|---|
401 | Invalid or missing API key. Check the Authorization header. |
402 | Insufficient balance. Top up to continue; requests resume immediately after credit. |
404 | Unknown model name or wrong endpoint path. |
429 | Rate limited. Slow down or retry with exponential backoff. |
500+ | Upstream or gateway error. Safe to retry once with backoff; contact support if it persists. |