All demosModStream
ModStream
Review live-chat messages before release and route risky content to moderation or care.
Powered by/yes-no/classify/rate
Performance & cost
This page session · since page load
- Typical request time
- —
- Input tokens
- 0
- Estimated cost · USD
- $0.00
How these numbers work · 0 successful requests
- Model compute
- —
- Successful requests
- 0
Average per measured successful request.
Run the demo to measure live requests.
Request time is the median time for a successful request, including queue, network, and retries. One request can judge many inputs: model compute adds their processing time and can exceed browser time.
Input tokens come from API response headers. Cost is estimated at $0.04 per million input tokens, before plan credits. Missing usage is marked unavailable or as a partial total (≥). Demo resets keep these totals; reload the page to start a new session.
Select Start chat stream, then open a held message to inspect its signals and moderation decision.
How it works
Messages wait for batched checks covering abuse, spam, safety and severity. A policy uses those results to release, hold, hide or escalate a message. Threshold changes update stored judgments without another request.
Demo scope
The chat is simulated. Abuse and personal distress can be confused, especially with indirect wording or unfamiliar slang. Some content remains held for human review; inspect decisions before applying this policy elsewhere.
Inspired by the work of dabit3.