AI Endpoints
Host models behind autoscaling, OpenAI-compatible inference endpoints.
Demo endpoints & metrics
Example request
Endpoints will accept OpenAI-compatible requests.
curl https://api.cloud.gbabilisim.ai/v1/endpoints/<endpoint-id>/chat/completions \
-H "Authorization: Bearer $GBA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "llama-3.1-8b-instruct", "messages": [{"role": "user", "content": "Hello"}]}'