Text model · #30 on the leaderboard

Llama 3 70B abliterated

meta-llama-3-70b-instruct-abliterated-v3.5 · built on Llama 3 70B Instruct · 8K context

Try it in chatGet an API key

What we measured

OpenUncensored Score
34.4
#30 on the leaderboard
Intelligence
21
Base model GPQA Diamond 37.9%, HLE 4.5%
Agentic
21
0% of tool tasks completed, 40% looped, 60% 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: 2.9s · 17 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": "meta-llama-3-70b-instruct-abliterated-v3.5", "messages": [{"role": "user", "content": "Hello"}]}'