Main endpoints
GET /v1/models— list the loaded modelPOST /v1/chat/completions— chat completion (stream or not)GET /docs— interactive docs (Swagger UI)GET /chat— web chat interface
Local OpenAI-compatible server running the {{ model_name }} model.
Open chat →GET /v1/models — list the loaded modelPOST /v1/chat/completions — chat completion (stream or not)GET /docs — interactive docs (Swagger UI)GET /chat — web chat interface
Point any OpenAI client at
{{ base_url }}/v1 using any key (authentication is ignored).
The full base URL is:
{{ base_url }}/v1
curl -X POST {{ base_url }}/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "{{ model_name }}",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": false
}'
from openai import OpenAI
client = OpenAI(
base_url="{{ base_url }}/v1",
api_key="ignored",
)
resp = client.chat.completions.create(
model="{{ model_name }}",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)