2796 次浏览 · 22 赞 · 2 转发 （收录时）
Perplexity 将 Fast Search 集成到其 Decisions API 中
- 谁
- Perplexity
- 引文
We're integrating Perplexity's Fast Search into the Perplexity Decisions API.
发生了什么
Perplexity 正在将 Fast Search 集成到 Perplexity Decisions API 中，使其能够以批处理模式做出决策，并以网络信息为事实依据。搜索费用为每次请求 $0.001，Decisions API 的费用为每 100 万个输入 token $0.02。Aravind Srinivas 还称，该 API 达到了最先进水平，是目前速度最快的 API。
接下来读什么
查看这件事的完整进展Perplexity Adds Fast Search to Its Decisions APIWe'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
这件事到目前为止
Perplexity is integrating Fast Search into its Decisions API so developers can make batch decisions grounded in web information. Search costs $0.001 per request, and Decisions API input costs $0.02 per 1 million tokens. Aravind Srinivas described the API as state of the art and the fastest available.
每天一封，跟上 AI 的重要变化
模型发布、价格变化、算力进展，附原始来源。免费，确认后开始发送，随时一键退订。 看一份往期日报 · 2026-11-04