REST API Reference

CSGHub-Lite starts its service by default on port 11435 of localhost, providing API interfaces compatible with Ollama and OpenAI.

API Overview

Method	Path	Description
GET	/api/health	Service health check
GET	/api/tags	List all local models
GET	/api/ps	View currently running models
POST	/api/show	Show detailed information for a specific model
POST	/api/pull	Pull model (supports streaming response)
POST	/api/stop	Stop and unload model
DELETE	/api/delete	Remove local model files
POST	/api/generate	Text generation (supports interactive stream)
POST	/api/chat	Chat conversation generation (supports stream)
POST	/v1/chat/completions	OpenAI-compatible chat interface
GET	/v1/models	OpenAI-compatible model list interface

Interface Examples

Chat API

curl http://localhost:11435/api/chat -d '{
  "model": "Qwen/Qwen3-0.6B-GGUF",
  "messages": [{"role": "user", "content": "Hello!"}]
}'

Non-Streaming Text Generation (Generate API)

curl http://localhost:11435/api/generate -d '{
  "model": "Qwen/Qwen3-0.6B-GGUF",
  "prompt": "Write a line of poetry about programming",
  "stream": false
}'

Get Running Models

curl http://localhost:11435/api/ps

OpenAI-Compatible Call (Python)

from openai import OpenAI

client = OpenAI(base_url="http://localhost:11435/v1", api_key="unused")

response = client.chat.completions.create(
    model="Qwen/Qwen3-0.6B-GGUF",
    messages=[{"role": "user", "content": "Hello, please introduce yourself."}]
)

print(response.choices[0].message.content)