Text model · #28 on the leaderboard

DeepSeek R1 Qwen Abliterated

deepseek-r1-distill-qwen-32b-abliterated · built on DeepSeek R1 Distill Qwen 32B · 16K context

Try it in chat Get an API key

What we measured

OpenUncensored Score

40.0

#28 on the leaderboard

Intelligence

Base model GPQA Diamond 61.5%, HLE 4.6%

Agentic

0% of tool tasks completed, 20% looped, 80% 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	$1.40	$1.40	$1.40

Requests go to the best provider first and fall back to the next if one fails. Speed in our test: 3.7s · 20 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": "deepseek-r1-distill-qwen-32b-abliterated", "messages": [{"role": "user", "content": "Hello"}]}'