Text model · #8 on the leaderboard
Apex Flash 1 Abliterated
glm-5.3-flash-apex-abliterated · built on GLM 5.3 Flash · 1M context
What we measured
OpenUncensored Score
63.2
#8 on the leaderboard
Intelligence
66
Base model GPQA Diamond 91.2%, HLE 39.9%
Agentic
70
60% of tool tasks completed, 0% looped, 40% crashed
Non-refusal
86%
of 36 edgy requests answered. Still refuses 100% 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 | $0.15 | $0.50 | $0.15 |
Requests go to the best provider first and fall back to the next if one fails. Live speed on real traffic: 6.4s · 11 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": "glm-5.3-flash-apex-abliterated", "messages": [{"role": "user", "content": "Hello"}]}'