AI 导读
我们正在将 Perplexity 的 Fast Search 集成到 Perplexity Decisions API 中。这使得批量模式下的决策可以基于来自网络的事实依据来做出。这是目前最先进、最快的 API。搜索每次请求收费 $0.001，Decisions API 每 1M 输入 token 收费 $0.02。
正文
We're integrating Perplexity's Fast Search into the Perplexity Decisions API. This allows for batch-mode decisions to be made with factual grounding from the web. State-of-the-art and the fastest API out there. Search costs $0.001 per request, and the Decisions API costs $0.02 per 1M input tokens.
The Decisions API can now search the web before it answers. A decision model returns a probability, but only knows what it saw in training, and your state. Add "mode": "web_grounding" and Fast Search runs one query per question, so pplx-decider-v1.2 answers from today's web.在 X 查看被引用的帖子
来源：Aravind Srinivas · x.com