Text model

Aion 3.5 Mini

aion-labs-aion-3-5-mini · 256K context

What we measured

OpenUncensored Score
–
Not ranked: missing published scores for its base model
Intelligence
–
Agentic
83
80% of tool tasks completed, 20% looped, 0% crashed
Non-refusal
94%
of 36 edgy requests answered. Still refuses 7% of hard-line ones.

How each number is measured is on the methodology page.

Providers and prices

ProviderStatusInput /MOutput /MCached input /M
Veniceonline$0.88$1.75$0.23

Requests go to the best provider first and fall back to the next if one fails. Speed in our test: 1.9s · 65 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": "aion-labs-aion-3-5-mini", "messages": [{"role": "user", "content": "Hello"}]}'