Commit

4ea8b7d

From what the commit approval speed tells and its potential demands, does it use jev-like LLMs for it?
OpenAI for now: - omni-moderation-latest — scores text and images for unsafe content. - gpt-6.1-sol — the configured model name for additional harmful-text and minors-in-images checks.
omni-moderation is neat because it can do both text and images, and it's free (rate-limited but /dev/null seems to fit within limits)
I'm not sure what role you are at /dev/null - but what's the plan when the demand goes beyond the limits?
Once you have purchased enough OpenAI credits, the limits go way up. Beyond that, you'd have to check with the /dev/null team
┌────────┬────────┬──────────────┬──────────────┬────────────┐
│ Tier   │ Spend¹ │ Requests/min │ Requests/day │ Tokens/min │
├────────┼────────┼──────────────┼──────────────┼────────────┤
│ Free   │ $0     │ 250          │ 5,000        │ 10,000     │
├────────┼────────┼──────────────┼──────────────┼────────────┤
│ Build  │ $5     │ 500          │ —            │ 20,000     │
├────────┼────────┼──────────────┼──────────────┼────────────┤
│ Launch │ $100   │ 2,000        │ —            │ 250,000    │
├────────┼────────┼──────────────┼──────────────┼────────────┤
│ Grow   │ $500   │ 5,000        │ —            │ 500,000    │
└────────┴────────┴──────────────┴──────────────┴────────────┘

¹ Total credits purchased, not monthly. Omni moderation is free. “—” means no daily cap listed.

commit 4ea8b7d