All demosChat Firehose

Chat Firehose

Find messages that need a moderator’s attention in a fast-moving chat stream.

Powered by/classify/rate

Ready to try it? Add your API key to run the model on these examples. Get a free key

Performance & cost

This page session · since page load

Ready to run
Typical request time
Input tokens
0
Estimated cost · USD
$0.00
How these numbers work · 0 successful requests
Model compute

Average per measured successful request.

Successful requests
0

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.

Try it

Start the stream, then inspect a flagged message or adjust a moderation threshold.

How it works

Messages are classified in batches. Flagged messages receive a severity check, and moderation thresholds decide which messages enter the review queue. Changing a threshold reuses the existing judgments.

Demo scope

The chat is simulated. Mixed intent, slang and multilingual messages can be misread. Messages handled by local fallback rules are labeled, and high traffic can exceed the model’s processing capacity.

Inspired by the work of dabit3.