Text model · #6 on the leaderboard
Abliterated Large Flash
abliterated-large-flash · built on DeepSeek V4.1 Flash 1017 · 1M context
What we measured
OpenUncensored Score
64.0
#6 on the leaderboard
Intelligence
68
Base model GPQA Diamond 91.7%, HLE 43.3%
Agentic
38
20% of tool tasks completed, 20% looped, 60% crashed
Non-refusal
92%
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 |
|---|---|---|---|---|
| Abliteration.ai | online | $1.00 | $2.00 | $0.10 |
| Venice | online | $1.25 | $2.50 | $0.13 |
| NanoGPT | online | $1.00 | $2.00 | $1.00 |
Requests go to the best provider first and fall back to the next if one fails. Live speed on real traffic: 1.0s · 159 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": "abliterated-large-flash", "messages": [{"role": "user", "content": "Hello"}]}'