Text model · #1 on the leaderboard

DeepSeek V4.1 Flash 1017 Uncensored

deepseek-v4.1-flash-1017-uncensored · built on DeepSeek V4.1 Flash 1017 · 1M context

Try it in chatGet an API key

What we measured

OpenUncensored Score
69.8
#1 on the leaderboard
Intelligence
68
Base model GPQA Diamond 91.7%, HLE 43.3%
Agentic
55
40% of tool tasks completed, 0% 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
Veniceonline$0.33$1.32$0.0083
NanoGPTonline$0.33$1.32$0.33

Requests go to the best provider first and fall back to the next if one fails. Live speed on real traffic: 577ms · 235 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-v4.1-flash-1017-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'