A100 LLM Gateway

Single-model local deployment backed by vLLM and protected by LLMGateway API keys.

Qwen active

Active Model

Model: qwen/qwen3.6-27b-thinking
Backend: vLLM on 2x A100 40GB
Context: 262144 tokens configured
HTTPS API: https://gateway.213-221-15-164.sslip.io/v1
HTTP API: http://213.221.15.164/v1

API Keys Provider Key Dashboard Playground

OpenAI-Compatible Call

Use a project API key from the API Keys page.

curl http://213.221.15.164/v1/chat/completions \
  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.6-27b-thinking",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 128
  }'