Text model · #27 on the leaderboard

DeepSeek R1 Llama 70B Abliterated

deepseek-r1-distill-llama-70b-abliterated · built on DeepSeek R1 Distill Llama 70B · 16K context

Try it in chatGet an API key

What we measured

OpenUncensored Score
40.4
#27 on the leaderboard
Intelligence
23
Base model GPQA Diamond 40.2%, HLE 5.1%
Agentic
40
20% of tool tasks completed, 0% 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

ProviderStatusInput /MOutput /MCached input /M
NanoGPTonline$0.70$0.70$0.70

Requests go to the best provider first and fall back to the next if one fails. Speed in our test: 6.7s · 18 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-llama-70b-abliterated", "messages": [{"role": "user", "content": "Hello"}]}'