Text model · #3 on the leaderboard

Qwen 3.8 27B Uncensored Fast by Heabsy

qwen3.8-27b-uncensored-fast · built on Qwen 3.8 27B · 512K context

Try it in chat Get an API key

What we measured

OpenUncensored Score

66.8

#3 on the leaderboard

Intelligence

Base model GPQA Diamond 90.5%, HLE 33.9%

Agentic

40% of tool tasks completed, 60% looped, 0% crashed

Non-refusal

100%

of 36 edgy requests answered. Still refuses 0% of hard-line ones.

How each number is measured is on the methodology page.

Providers and prices

Provider	Status	Input /M	Output /M	Cached input /M
NanoGPT	online	$1.00	$3.00	$1.00

Requests go to the best provider first and fall back to the next if one fails. Speed in our test: 594ms · 252 tok/s.

Call it

curl https://openuncensored.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3.8-27b-uncensored-fast", "messages": [{"role": "user", "content": "Hello"}]}'