Inference API

An OpenAI-compatible inference endpoint.

The server supplies its single available model automatically. Omit the model field, or use default when a client requires one.

Usage

Send the API key as a bearer token:

curl https://inference.lulzx.space/v1/chat/completions   -H "Authorization: Bearer $API_KEY"   -H "Content-Type: application/json"   -d '{
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256
  }'

Python:

from openai import OpenAI

client = OpenAI(
    base_url="https://inference.lulzx.space/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="default",
    messages=[{"role": "user", "content": "Hello"}],
)

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

Endpoints

• POST /v1/chat/completions
• POST /v1/completions
• POST /v1/responses
• POST /v1/messages
• GET /v1/models returns the neutral identifier default

Limit: 30 requests per minute per address, 2 concurrent inference requests.

Statistics

This service is provided as-is and may be unavailable when the inference host is offline.