Inference

    API Reference

    Confirmed request conventions for InferX production endpoints.

    Confirmed public interface

    InferX exposes OpenAI-compatible production endpoints. The current public workflow provides an API Base URL, Model Name, and API Key through the InferX Console.

    Request conventions

    Inference calls use bearer authentication and an OpenAI-compatible chat completions request shape. Use the URL and model identifier supplied for your endpoint.

    curl
    curl -X POST "$INFERX_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $INFERX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

    Legacy management reference