How are you handling the unit costs, rate limits, and model risk? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jsemrau on June 27, 2024 \| parent \| context \| favorite \| on: Show HN: Find AI – Perplexity Meets LinkedIn How are you handling the unit costs, rate limits, and model risk?

philip1209 on June 27, 2024 [–]

That’s a deep question. Under the hood we use some LLM gateways like Helicone and https://usevelvet.com to track cost per request and optimize it.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact