README.md

metadata

title: Qwen3.5-0.8B Text API
emoji: 🔮
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 7860

Qwen3.5-0.8B Text API

Text inference service using Qwen3.5-0.8B ONNX. Non-streaming JSON responses.

Endpoints

POST /prompt

Text-only inference. Returns full response in one JSON body (no streaming).

Body (JSON):

• prompt (required) - Text prompt
• max_tokens (optional) - Max tokens to generate (default: 256)

Response: { "response": "..." }

Auth: If API_KEY env var is set, send it via header X-API-Key: <key> or Authorization: Bearer <key>. If unset, no auth.

GET /health

Health check and model load status (no auth).

Usage

# Without API key (when API_KEY is not set)
curl -X POST "http://localhost:7860/prompt" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "What is 2+2?"}'

# With API key
curl -X POST "http://localhost:7860/prompt" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-secret-key" \
  -d '{"prompt": "What is 2+2?"}'

Set API_KEY in the environment to enable protection (e.g. API_KEY=your-secret-key node server.js).