AI Cafe ✨

Welcome! From 2 to 7PM, you can use this AI unlimitedly to your AI tools.

API base URL

https://2laljgmiflma8y-8000.proxy.runpod.net/v1

Available Model

• Model ID: openai/qwen3.6-27b
• Context length: 16K tokens
• Typical latency: ~7 seconds per request

Authentication

Use any placeholder value, for example dummy.

Aider

Use Aider with these flags:

aider \\
  --openai-api-base https://2laljgmiflma8y-8000.proxy.runpod.net/v1 \\
  --openai-api-key dummy \\
  --model openai/qwen3.6-27b \\
  --no-auto-commits

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://2laljgmiflma8y-8000.proxy.runpod.net/v1",
    api_key="dummy",
)

response = client.chat.completions.create(
    model="openai/qwen3.6-27b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

cURL

curl https://2laljgmiflma8y-8000.proxy.runpod.net/v1/chat/completions \\
  -H "Content-Type: application/json" \\
  -H "Authorization: Bearer dummy" \\
  -d '{
    "model": "openai/qwen3.6-27b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Happy coding! From Rumah Roti Sourdough x Fydemy ❤️