SDK Guides
curl
Call the Yaha gateway with raw HTTP requests.
Use curl for a quick smoke test or to verify your yaha.* key and model allowlist.
Chat completion
curl https://gateway.yahagateway.io/v1/chat/completions \
-H "Authorization: Bearer yaha.YOUR_PROJECT_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-mini",
"messages": [{"role": "user", "content": "Hello"}]
}'Streaming
Add "stream": true to the JSON body. The response is Server-Sent Events (text/event-stream).
curl -N https://gateway.yahagateway.io/v1/chat/completions \
-H "Authorization: Bearer yaha.YOUR_PROJECT_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-mini",
"stream": true,
"messages": [{"role": "user", "content": "Hello"}]
}'List models
curl https://gateway.yahagateway.io/v1/models \
-H "Authorization: Bearer yaha.YOUR_PROJECT_KEY"Notes
- Replace
yaha.YOUR_PROJECT_KEYwith your full project key from the console. - The gateway implements OpenAI-compatible
/v1/*endpoints. - See Prerequisites if you get
403or model errors. - See Language examples for additional languages and a reusable integration prompt.