---
title: "Perplexity AI — Perplexity AI（搜索问答产品）"
source: "https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89"
wiki: "systems-analysis.info/int"
article: "Perplexity_AI_—_Perplexity_AI（搜索问答产品）"
language: "zh"
categories:
  - "Category:Chinese"
revision_id: 5568
wiki_created_at: 2026-09-06T23:51:08Z
wiki_modified_at: 2026-09-06T23:51:08Z
downloaded_at: 2026-09-07T23:09:12Z
---

# Perplexity AI — Perplexity AI（搜索问答产品）

**Perplexity AI** 是一家美国初创公司，也是一款同名的**对话式搜索引擎** (conversational search engine)，它利用人工智能为用户的查询提供直接答案，并附上信息来源<sup>[\[1\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-wikipedia-ru-pplx-1)</sup>。该公司于2022年由来自OpenAI、Meta、Google、DeepMind和Databricks的专家团队创立<sup>[\[2\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-rbc-trends-2)</sup>。

该平台结合了自有的大型语言模型 (LLM) 和对其他公司领先模型的访问权限，从而能够优化答案的速度、准确性和成本。Perplexity的核心技术是先进的**检索增强生成 (Retrieval-Augmented Generation, RAG)**系统，该系统利用其自有的搜索基础设施中的最新信息来丰富LLM的回答<sup>[\[3\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-pplx-rag-intro-3)</sup>。

## 历史与创始人

Perplexity AI 公司于2022年由四位专家创立：

- **Aravind Srinivas** (首席执行官 CEO) — 曾任 OpenAI、Google Brain 和 DeepMind 的研究员<sup>[\[4\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-wiki-eng-shrinivas-4)</sup>。
- **Denis Yarats** (首席技术官 CTO) — 曾任 Meta AI 的研究科学家。
- **Johnny Ho** (首席战略官 CSO) — 曾任 Quora 工程师。
- **Andy Konwinski** — Databricks 联合创始人<sup>[\[2\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-rbc-trends-2)</sup>。

最初，该项目被设想为用于数据分析的 B2B 服务，但在2022年10月，团队基于 Bing 和 GPT-3 开发了一个搜索引擎原型，这决定了公司的未来发展方向<sup>[\[5\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-forbes-ru-story-5)</sup>。

Perplexity AI 吸引了包括 Nvidia、软银 (SoftBank) 和亚马逊创始人杰夫·贝索斯 (Jeff Bezos) 在内的主要投资者的巨额投资。到2025年初，公司估值达到**140亿美元**<sup>[\[6\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-vashgolos-14b-6)</sup>，月活跃用户超过**1500万**<sup>[\[7\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-3dnews-growth-7)</sup>。

## 技术架构

### Retrieval-Augmented Generation (RAG) - 检索增强生成

Perplexity 的基础是 **RAG** 技术，它能克服传统 LLM 的局限性，例如知识陈旧和“幻觉”。其工作流程包括以下几个阶段<sup>[\[8\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-timeweb-rag-8)</sup>：

1.  分析并重构用户查询，以实现最佳搜索。
2.  使用**自有的搜索基础设施**（网络爬虫和排名系统）进行信息检索，该系统优先考虑权威和非SEO来源<sup>[\[7\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-3dnews-growth-7)</sup>。
3.  从找到的网页中提取最相关的片段（“snippets”）。
4.  利用 LLM 基于这些片段生成连贯、准确的回答。
5.  生成答案时附带**引文**和原始来源链接。

### 多模型策略

Perplexity 采用混合方法，结合自有模型和第三方模型，以实现速度、准确性和成本之间的平衡<sup>[\[9\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-kedprof-claude-9)</sup>。

- 免费版中，为了快速响应，通常使用 **Claude 3 Haiku**。
- 付费的 Pro 版中，可使用更强大的模型，如 **Claude 3.5 Sonnet** 和 **GPT-4o**。

拥有 **Perplexity Pro** 订阅的用户可以手动从多种模型中进行选择，包括<sup>[\[10\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-pplx-pro-models-10)</sup>：

- **OpenAI**: GPT-4o, GPT-4 Turbo
- **Anthropic**: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku
- **Google**: Gemini 2.5 Pro
- **Meta**: Llama 3
- **Mistral AI**: Mistral Large
- **xAI**: Grok-3 Beta
- Perplexity 自有模型。

## Perplexity 的自有模型

该公司开发了专为搜索任务和处理互联网最新信息而优化的自有模型。

### PPLX 系列（早期模型）

Perplexity 首批通过 API 提供的自有模型是 **pplx-7b-online** 和 **pplx-70b-online**，于2023年12月推出<sup>[\[11\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-marktechpost-pplx-11)</sup>。它们分别基于微调版的 **Mistral 7B** 和 **Llama 2 70B**，专注于处理在线数据<sup>[\[12\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-pplx-blog-online-llms-12)</sup>。

### Sonar 系列（当前一代）

**Sonar** 是旗舰模型系列，基于 Meta 的 **Llama 3.1 70B** 构建，但经过了额外的微调，以提高搜索模式下答案的事实准确性和可读性<sup>[\[13\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-pplx-blog-new-sonar-13)</sup>。

Sonar 的主要特点：

- **高速度**: 得益于与 **Cerebras** 的合作及其专用的推理基础设施，Sonar 的生成速度高达每秒 **1200 个词元**，比 Gemini 2.0 Flash 快近10倍<sup>[\[14\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-cerebras-partnership-14)</sup>。
- **推测解码技术**: 为了进一步加速生成，使用了一个大小为1B的自有“草稿模型”，它允许主模型在一次传递中生成多个词元<sup>[\[15\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-pplx-blog-speculation-15)</sup>。
- **高性能**: 在 LM Arena 的 **Search Arena** 评估中，**Sonar-Reasoning-Pro** 模型排名第一，在统计上与 Gemini-2.5-Pro-Grounding 持平<sup>[\[16\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-pplx-blog-search-arena-16)</sup>。

## API and Enterprise Solutions - API 与企业解决方案

Perplexity 通过 **Sonar API** 和 **Sonar Pro API** 为开发者和企业客户提供对其模型的访问。这些 API 针对速度和易用性进行了优化，包括引用功能和自定义搜索源的选项。Perplexity 的解决方案被用于各行各业，以创建原生搜索引擎和自动化研究任务<sup>[\[17\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-pplx-blog-sonar-pro-api-17)</sup>。

## 对比分析与用户体验

Perplexity 的性能因任务类型而异。

- 在需要基于最新数据进行高事实准确性判断的任务中（例如放射学分析），Perplexity 表现出**最高的准确率 (0.83)**，优于 Claude、Bing 和 ChatGPT<sup>[\[18\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-thieme-radiology-18)</sup>。
- 在涉及罕见或高度专业化知识的任务中（例如罕见疾病），Perplexity 可能会输给知识库更广泛的模型，如 ChatGPT 和 Gemini<sup>[\[19\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-mdpi-rare-disease-19)</sup>。

一项可用性研究 (SUS) 表明，尽管 Google 和 Perplexity 两个平台都可接受，但 Google 的得分 (82.29) 高于 Perplexity (73.98)。这归因于用户对 Google 界面的熟悉，以及 Perplexity 提供了创新但不太熟悉的功能，导致学习曲线更陡峭<sup>[\[20\]](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_note-ieee-usability-20)</sup>。

## 外部链接

- <a href="https://www.perplexity.ai/" class="external text" rel="nofollow">Perplexity AI 官方网站</a>
- <a href="https://www.perplexity.ai/hub/blog/" class="external text" rel="nofollow">Perplexity 官方博客</a>

## 参考文献

- Chen, C.; et al. (2023). *Accelerating Large Language Model Decoding with Speculative Sampling*. <a href="https://arxiv.org/abs/2302.01318" class="external text" rel="nofollow">arXiv:2302.01318</a>.
- Zhang, J.; et al. (2023). *Draft & Verify: Lossless Large Language Model Acceleration via Self‑Speculative Decoding*. <a href="https://arxiv.org/abs/2309.08168" class="external text" rel="nofollow">arXiv:2309.08168</a>.
- Chen, H.; et al. (2024). *Retrieval‑Augmented Generation for Large Language Models: A Survey*. <a href="https://arxiv.org/abs/2312.10997" class="external text" rel="nofollow">arXiv:2312.10997</a>.
- Soudani, H.; et al. (2024). *Fine‑Tuning vs. Retrieval‑Augmented Generation for Less‑Popular Knowledge*. <a href="https://arxiv.org/abs/2403.01432" class="external text" rel="nofollow">arXiv:2403.01432</a>.
- Chen, Y.; et al. (2024). *Evaluation of Retrieval‑Augmented Generation: A Survey*. <a href="https://arxiv.org/abs/2405.07437" class="external text" rel="nofollow">arXiv:2405.07437</a>.
- Hsieh, C.‑P.; et al. (2024). *RULER: What's the Real Context Size of Your Long‑Context Language Models?*. <a href="https://arxiv.org/abs/2404.06654" class="external text" rel="nofollow">arXiv:2404.06654</a>.
- Arena Team (2025). *Search Arena: Analyzing Search‑Augmented Large Language Models*. <a href="https://arxiv.org/abs/2506.05334" class="external text" rel="nofollow">arXiv:2506.05334</a>.
- Zhu, W.; et al. (2025). *PSC: Extending Context Windows via Phase Shift Calibration*. <a href="https://arxiv.org/abs/2505.12423" class="external text" rel="nofollow">arXiv:2505.12423</a>.
- Yu, L.; et al. (2025). *Synergizing RAG and Reasoning: A Systematic Review*. <a href="https://arxiv.org/abs/2504.15909" class="external text" rel="nofollow">arXiv:2504.15909</a>.
- Chen, X.; et al. (2025). *Universal Embeddings for Multimodal Multilingual Retrieval*. <a href="https://arxiv.org/abs/2506.18902" class="external text" rel="nofollow">arXiv:2506.18902</a>.

## 注释

1.  <span id="cite_note-wikipedia-ru-pplx-1">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-wikipedia-ru-pplx_1-0) “Perplexity.ai”. 维基百科，自由的百科全书. <a href="https://ru.wikipedia.org/wiki/Perplexity.ai" class="external autonumber" rel="nofollow">[1]</a></span>
2.  <span id="cite_note-rbc-trends-2">↑ <sup>[2.0](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-rbc-trends_2-0)</sup> <sup>[2.1](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-rbc-trends_2-1)</sup> “Perplexity AI — 谷歌杀手还是昙花一现”. *RBC Trends*. <a href="https://trends.rbc.ru/trends/industry/668bba599a79472bf71c43cd" class="external autonumber" rel="nofollow">[2]</a></span>
3.  <span id="cite_note-pplx-rag-intro-3">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-pplx-rag-intro_3-0) “An Introduction to RAG Models”. *Perplexity AI*. <a href="https://www.perplexity.ai/page/an-introduction-to-rag-models-jBULt6_mSB2yAV8b17WLDA" class="external autonumber" rel="nofollow">[3]</a></span>
4.  <span id="cite_note-wiki-eng-shrinivas-4">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-wiki-eng-shrinivas_4-0) “Aravind Srinivas”. In *Wikipedia*. <a href="https://en.wikipedia.org/wiki/Aravind_Srinivas" class="external autonumber" rel="nofollow">[4]</a></span>
5.  <span id="cite_note-forbes-ru-story-5">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-forbes-ru-story_5-0) Belousova, Anastasia. “白俄罗斯人如何与合作伙伴共同打造出全球最昂贵的初创公司之一Perplexity”. *Forbes.ru*. <a href="https://www.forbes.ru/svoi-biznes/526489-kak-belorus-s-partnerami-postroili-odin-iz-samyh-dorogih-startapov-v-mire-perplexity" class="external autonumber" rel="nofollow">[5]</a></span>
6.  <span id="cite_note-vashgolos-14b-6">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-vashgolos-14b_6-0) “初创公司Perplexity AI估值达140亿美元”. *Ваш голос*. <a href="https://vashgolos.net/news/87429" class="external autonumber" rel="nofollow">[6]</a></span>
7.  <span id="cite_note-3dnews-growth-7">↑ <sup>[7.0](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-3dnews-growth_7-0)</sup> <sup>[7.1](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-3dnews-growth_7-1)</sup> “基于AI的搜索引擎Perplexity实现爆炸性增长，准备与谷歌竞争”. *3DNews*. <a href="https://3dnews.ru/1109254/poiskovaya-sistema-perplexity-na-baze-ii-pokazala-burniy-rost-i-gotova-k-onkurirovat-s-google" class="external autonumber" rel="nofollow">[7]</a></span>
8.  <span id="cite_note-timeweb-rag-8">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-timeweb-rag_8-0) “Perplexity：这是什么神经网络，如何工作以及为何需要它”. *TimeWeb.Cloud*. <a href="https://timeweb.cloud/blog/perplexity-chto-eto-za-nejroset" class="external autonumber" rel="nofollow">[8]</a></span>
9.  <span id="cite_note-kedprof-claude-9">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-kedprof-claude_9-0) “Perplexity与Claude AI：提供精准答案的引擎”. *Кедр.pro*. <a href="https://kedprof.ru/tpost/ofug8mo051-perplexity-i-claude-ai-dvizhok-dlya-toch" class="external autonumber" rel="nofollow">[9]</a></span>
10. <span id="cite_note-pplx-pro-models-10">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-pplx-pro-models_10-0) “What advanced AI models are included in a Perplexity Pro subscription?”. *Perplexity Help Center*. <a href="https://www.perplexity.ai/help-center/en/articles/10354919-what-advanced-ai-models-are-included-in-a-perplexity-pro-subscription" class="external autonumber" rel="nofollow">[10]</a></span>
11. <span id="cite_note-marktechpost-pplx-11">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-marktechpost-pplx_11-0) “Perplexity Unveils Two New Online LLM Models: pplx-7b-online and pplx-70b-online”. *MarkTechPost*. <a href="https://www.marktechpost.com/2023/12/03/perplexity-unveils-two-new-online-llm-models-pplx-7b-online-and-pplx-70b-online/" class="external autonumber" rel="nofollow">[11]</a></span>
12. <span id="cite_note-pplx-blog-online-llms-12">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-pplx-blog-online-llms_12-0) “Introducing PPLX Online LLMs”. *Perplexity Blog*. <a href="https://www.perplexity.ai/hub/blog/introducing-pplx-online-llms" class="external autonumber" rel="nofollow">[12]</a></span>
13. <span id="cite_note-pplx-blog-new-sonar-13">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-pplx-blog-new-sonar_13-0) “Meet a new era of Perplexity Sonar”. *Perplexity Blog*. <a href="https://www.perplexity.ai/hub/blog/meet-new-sonar" class="external autonumber" rel="nofollow">[13]</a></span>
14. <span id="cite_note-cerebras-partnership-14">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-cerebras-partnership_14-0) “Cerebras Powers Perplexity Sonar with Industry's Fastest AI Inference”. *Cerebras Press Release*. <a href="https://www.cerebras.ai/press-release/cerebras-powers-perplexity-sonar-with-industrys-fastest-ai-inference" class="external autonumber" rel="nofollow">[14]</a></span>
15. <span id="cite_note-pplx-blog-speculation-15">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-pplx-blog-speculation_15-0) “Accelerating Sonar through Speculation”. *Perplexity Blog*. <a href="https://www.perplexity.ai/hub/blog/accelerating-sonar-through-speculation" class="external autonumber" rel="nofollow">[15]</a></span>
16. <span id="cite_note-pplx-blog-search-arena-16">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-pplx-blog-search-arena_16-0) “Perplexity Sonar Dominates New Search Arena”. *Perplexity Blog*. <a href="https://www.perplexity.ai/hub/blog/perplexity-sonar-dominates-new-search-arena-evolution" class="external autonumber" rel="nofollow">[16]</a></span>
17. <span id="cite_note-pplx-blog-sonar-pro-api-17">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-pplx-blog-sonar-pro-api_17-0) “Introducing the Sonar Pro API”. *Perplexity Blog*. <a href="https://www.perplexity.ai/hub/blog/introducing-the-sonar-pro-api" class="external autonumber" rel="nofollow">[17]</a></span>
18. <span id="cite_note-thieme-radiology-18">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-thieme-radiology_18-0) “Comparative Analysis of Large Language Models for Question Answering in Radiology”. *Thieme Connect*. <a href="http://www.thieme-connect.de/DOI/DOI?10.1055/s-0044-1787974" class="external autonumber" rel="nofollow">[18]</a></span>
19. <span id="cite_note-mdpi-rare-disease-19">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-mdpi-rare-disease_19-0) “A Comparative Study of AI Chatbots in Answering Questions on Rare Diseases”. *MDPI*. <a href="https://www.mdpi.com/2075-4418/15/6/672" class="external autonumber" rel="nofollow">[19]</a></span>
20. <span id="cite_note-ieee-usability-20">[↑](https://systems-analysis.info/int/Perplexity_AI_%E2%80%94_Perplexity_AI%EF%BC%88%E6%90%9C%E7%B4%A2%E9%97%AE%E7%AD%94%E4%BA%A7%E5%93%81%EF%BC%89#cite_ref-ieee-usability_20-0) “Usability and User Satisfaction of Google Search and Perplexity AI”. *IEEE Xplore*. <a href="https://ieeexplore.ieee.org/document/10957499/" class="external autonumber" rel="nofollow">[20]</a></span>
