← 返回归档

帖子详情

查看 X 原文
A
Aravind Srinivas@AravSrinivas
At 1 cent per million input tokens for decision models (the pricing we offer for pplx-decider-flash), you basically spend at best $10,000 for a quadrillion input tokens. We're going to optimize inference and caching (of inputs) even further. docs.perplexity.ai/docs/decisions…
帖子 ID
2111184937919594786
Markdown
/app/data/archive/2026/10/16/AravSrinivas/2111184937919594786/post.md
保存状态
complete
查看 Markdown 内容
---
tweet_id: "2111184937919594786"
author: "AravSrinivas"
published_at: "2026-10-16T19:58:07+00:00"
source_url: "https://x.com/AravSrinivas/status/2111184937919594786"
---

At 1 cent per million input tokens for decision models (the pricing we offer for pplx-decider-flash), you basically spend at best $10,000 for a quadrillion input tokens. We're going to optimize inference and caching (of inputs) even further. [docs.perplexity.ai/docs/decisions…](https://docs.perplexity.ai/docs/decisions/quickstart)