Runware launches two API content moderation models that take plain-language policies
aziz4ai · x · 2026-10-07
Runware has released two content moderation safety classifiers on its API.
The key twist: instead of fixed categories, you describe your content policy in plain language, include it in the prompt, and the models judge content against that policy — making custom moderation rules much easier to set up.
More from Models
- Hermes Index scores: Opus 5.5 at $4.99/task leads, GPT 6 Astra costs $11.61 — NousResearch · 2026-10-07
- Nous Research launches Hermes Index agent leaderboard, Claude Opus 5.5 tops at 63.31 — NousResearch · 2026-10-07
- Testing Mistral Large 4 on FPS: 151K Reasoning Tokens Later, Still Rough — qtnx_ · 2026-10-07
- Many Mistral Large 4 failures traced to reasoning mode not being enabled — qtnx_ · 2026-10-07
- Early Opus 5.5 user says hype is overblown: shortcuts, wrong assumptions, sloppy work — haider1 · 2026-10-07
- TypeSafe's Jev model bets on machine-native intelligence over text-optimized LLMs — TWIML AI Podcast · 2026-10-07