"Where knowledge begins"
Perplexity Sonar is a family of models for AI search, web-based answers, research, reasoning, and deep research. The API is particularly strong in current facts, citations, product comparisons, summaries, and research workflows.
Perplexity Sonar
LLM “Where knowledge begins”
Location: USA ⓘ Perplexity AI, Inc., 115 Sansome St, Ste 900, San Francisco, CA 94104-3624, USA
Target audience
Perplexity Sonar is aimed at developers, media companies, analysts, SEO/GEO teams, consultants, knowledge workers, market researchers, and businesses that want to combine up-to-date web information with LLM responses and sources.
Outstanding features
Sonar’s key strength is the combination of web search, LLM responses, and source citations. The API is particularly interesting because Perplexity documents Zero Data Retention for the Sonar API and does not use customer data for model training.
Main use cases
Sonar is suitable for up-to-date research, news monitoring, market analysis, product comparisons, SEO/GEO research, source verification, competitive analysis, RAG extensions, and automated research reports.
Usage & notes
Sonar is ideal when timeliness and sources matter more than creative generation. For highly regulated EU applications, companies should still review the DPA, server region, enterprise retention, and role/permission concepts.
| Target audience | Assessment |
|---|---|
| Private individuals | Conditionally – Perplexity as an app is user-friendly; Sonar as an API is more developer-oriented. |
| Self-employed / freelancers | Yes – suitable for research tools, up-to-date answers, source-based work, market analysis, and content research. |
| SMEs | Yes – especially for web search, RAG-adjacent research, up-to-date information queries, and internal tools. |
| Large enterprises | Yes, with Enterprise/API review – Zero Data Retention for the Sonar API, enterprise security features, and SOC 2 Type II are positives. |
| Developers / teams | Very well suited – API for Sonar, Sonar Pro, Sonar Reasoning Pro, Deep Research, Search API, Embeddings, and OpenAI-like integration. |
| Privacy-sensitive organizations | Conditional to good – the Sonar API is strong because of Zero Data Retention; the North America server location and the lack of a publicly reviewed DPA within the research scope still need to be checked. |
Perplexity Sonar – Model overview
| Model / API | Type | Best suited for |
|---|---|---|
| sonar | Search Model | Fast fact-based answers, up-to-date web search, simple summaries, product comparisons. (Perplexity) |
| sonar pro | Search Model | More complex web research, better synthesis, longer answers, professional research workflows. (Perplexity) |
| sonar reasoning pro | Reasoning Model | Multi-step reasoning tasks, complex questions, structured analysis with web context. (Perplexity) |
| sonar deep research | Research Model | Detailed reports, in-depth research, market analyses, topic dossiers. (Perplexity) |
| Search API | Search API | Real-time web search as a building block for RAG, apps, and internal tools. (Perplexity AI) |
| Agent API | Agent API | Model-agnostic agents with web search and URL fetching; also uses third-party models. (Perplexity AI) |
| Embeddings API | Embedding API | Semantic search, RAG, similarity search, knowledge bases. (Perplexity AI) |
Hosting & Data
1) On-prem / local hosting
Meaning: The company operates the solution on its own hardware or within its own infrastructure. In the strictest sense, not only the application runs locally, but ideally the model as well.
2) Private cloud / data center
Meaning: The solution runs in a dedicated or more clearly separated cloud environment, often with a hosting provider or hyperscaler, but in a German data center or in a particularly controlled environment.
3) EU SaaS / managed
Meaning: The provider operates the solution itself as a service. The company uses the tool as a ready-made cloud service, ideally with EU data residency.
4) Hybrid
Meaning: One part of the processing remains internal / local / in a private cloud, while another part runs in an external cloud or EU SaaS.
5) AVV / DPA
Meaning: This is the data processing agreement or Data Processing Addendum. It governs that the provider processes personal data on behalf of the customer and is bound by the customer's instructions.
6) No training
Meaning: The provider does not use your prompts, uploads, attachments, chat histories, or outputs for training or improving the general model — ideally excluded by contract.
7) Open-source / transparency path
Meaning: There is a path toward greater technical transparency and sovereignty, for example through:
- open models
- documented components
- self-hostable parts
- traceable architecture
- export / switching options
| On-prem / local hosting | ❓ |
| Private cloud / data center | ❓ |
| EU SaaS / Managed | ❓ |
| Hybrid | ⚠️ |
| DPA / AVV | ⚠️ |
| No training on customer data | ✅ |
| Open source / transparency path | ⚠️ |
Overall assessment:
API/SaaS LLM search with a strong privacy promise for the Sonar API, but no on-prem or self-hosting. Perplexity Sonar is provided as an API for web-based answers, research, reasoning, and deep research. Hosting model: SaaS/API; according to the Perplexity FAQ, compute runs on Amazon Web Services in North America. On-prem, local hosting, or private cloud for Sonar are not confirmed as standard offerings in the official sources. Data processing: According to Perplexity, Zero Data Retention applies to the Sonar API; API prompts and responses are not stored and are not used for training. Only billing metadata is collected, without content data. Enterprise: Perplexity states that it does not use Enterprise customer data for training or fine-tuning; according to the Help Center, files uploaded in Enterprise are automatically deleted after seven days, while threads and organizational data remain unless deleted or removal is requested. Integrations/products: Sonar, Sonar Pro, Sonar Reasoning Pro, Sonar Deep Research, Search API, Embeddings, Agent API, and Enterprise features such as SSO, SCIM, audit logs, connector controls, and file retention settings.
Conclusion:
Very well suited for current, source-based LLM answers via API; for strictly regulated EU use, only deploy with contractual and transfer review due to North America hosting.
| On-prem / local hosting | ❓ |
| Private cloud / data center | ❓ |
| EU SaaS / Managed | ❓ |
| Hybrid | ⚠️ |
| DPA / AVV | ⚠️ |
| No training on customer data | ✅ |
| Open source / transparency path | ⚠️ |
Overall assessment:
API/SaaS LLM search with a strong privacy promise for the Sonar API, but no on-prem or self-hosting. Perplexity Sonar is provided as an API for web-based answers, research, reasoning, and deep research. Hosting model: SaaS/API; according to the Perplexity FAQ, compute runs on Amazon Web Services in North America. On-prem, local hosting, or private cloud for Sonar are not confirmed as standard offerings in the official sources. Data processing: According to Perplexity, Zero Data Retention applies to the Sonar API; API prompts and responses are not stored and are not used for training. Only billing metadata is collected, without content data. Enterprise: Perplexity states that it does not use Enterprise customer data for training or fine-tuning; according to the Help Center, files uploaded in Enterprise are automatically deleted after seven days, while threads and organizational data remain unless deleted or removal is requested. Integrations/products: Sonar, Sonar Pro, Sonar Reasoning Pro, Sonar Deep Research, Search API, Embeddings, Agent API, and Enterprise features such as SSO, SCIM, audit logs, connector controls, and file retention settings.
Conclusion:
Very well suited for current, source-based LLM answers via API; for strictly regulated EU use, only deploy with contractual and transfer review due to North America hosting.
Strengths & weaknesses at a glance
| Strengths | Weaknesses |
|---|---|
| • Very good for up-to-date research. | • Not available as an on-prem model. |
| • Source-based answers. | • No open-weight model. |
| • Sonar API with Zero Data Retention. | • Server region/EU-only is not clearly documented publicly. |
| • No training on API customer data according to the official API documentation. | • Consumer app privacy differs from the Sonar API. |
| • SOC 2 Type II and enterprise security documentation. | • For highly confidential research, an enterprise contract and Trust Center review are necessary. |
Reviews
0 reviews in total
There are no confirmed reviews for this tool yet.
Submit review
Your review will only become visible after email confirmation. This protects the portal against abuse.
Report review
Please select the reason why this review should be checked.
GDPR-compliant usage possible?
Overall assessment: Conditionally to well suited for GDPR compliance for the Sonar API, depending on the contract.
Positive is that Perplexity states a strict Zero Data Retention Policy for the Sonar API: content from API requests is not stored and customer data is not used for model training. According to the API documentation, only necessary billing metrics are collected, such as token count, model used, timestamp, duration, and API key identification; according to Perplexity, this metadata does not contain prompt or response content. In addition, Perplexity mentions SOC 2 Type II, HIPAA Gap Assessment, and CAIQlite in the trust/security context.
Negative is that, according to the FAQ, Perplexity hosts its compute infrastructure via AWS in North America; for EU customers, this means a third-country/transfer assessment is required. No verified information is available in the evaluated sources about a publicly directly reviewed DPA/AVV or SCC document.
Server location: AWS in North America for language models/API according to the Perplexity FAQ. Conclusion: For API-based research and search applications, significantly more attractive from a data protection perspective than many LLM APIs, but for GDPR-compliant EU use, the DPA/AVV, transfer mechanism, subprocessors, and enterprise contract should be reviewed. Sources: Perplexity Privacy & Security, FAQ, and Enterprise Security information.