EMPERO / 00 — FREE

Qwen3.8-FP8

Free community endpoint for Qwen3.8-FP8 — a thank-you for 2,000 followers on @EmperoAI.

OpenAI-compatible. Point any client at https://free.empero.org/v1. Any API key is accepted (use free if the client insists).

Open the playground ↗ empero.org Hugging Face

from openai import OpenAI
client = OpenAI(base_url="https://free.empero.org/v1", api_key="free")
print(client.chat.completions.create(
    model="Qwen/Qwen3.8-27B-FP8",
    messages=[{"role": "user", "content": "Say hi from Qwen3.8-FP8."}],
).choices[0].message.content)

• 01
  ModelQwen/Qwen3.8-27B-FP8aliases free, qwen3.8-fp8
• 02
  Context131,072 tokens · default max_tokens 32,768
• 03
  Hardware2× RTX PRO 6000 — please be kind. Generous chat limits, no VPNs / datacenters.
• 04
  LoggingPrompts and completions are logged (IPs hashed) so we can train a better open model later.