Conversational Insights API 429 errors during JMeter load test

Trying to understand the rate limits for the Conversational Insights API in Genesys Cloud US1. Running JMeter 5.6 with 100 concurrent users against GET /api/v2/conversation/analytics/details. The endpoint returns HTTP 429 Too Many Requests immediately. Standard flow works fine at lower concurrency. Is there a specific throttle for this AI endpoint compared to WFM APIs?

Thanks for the help.