Skip to content
On this page

Inference

Moderations

Classify content with an [OI] moderation model.

POST/v1/moderationsAPI key
curl -X POST https://api.relayrouter.org/v1/moderations \
-H "Authorization: Bearer $RELAY_API_KEY" \
-H 'content-type: application/json' \
-d '{
"model": "omni-moderation-latest",
"input": "text to classify"
}'

Moderations use the openai provider by default, or an openai_compatible provider named in the provider field. The response is the upstream JSON passed through.

Billing

Moderation calls are logged for analytics and normally cost nothing. A positive per-account network_fee_micro is still charged. Use /usage as the source of truth for the recorded amount.