"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
Sonar Pro Advanced search with grounding for more complex questions, follow-ups, and optional Pro Search with multi-step tool use.
Sonar Reasoning Pro Reasoning model for complex, multi-step analysis and inference tasks with web context.
Sonar Deep Research Research model for comprehensive investigations across many sources, detailed reports, and deeper analyses.
Search API Separate API access for raw web search results with filters, without token-based response generation.
Embeddings API Embedding models for semantic search, RAG, retrieval, and machine learning applications.
AWS Marketplace API credits can be obtained via AWS Marketplace with consolidated billing and enterprise procurement.
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 | ⚠️ |
On-Prem / local hosting: indirect / not available
No on-premise, local, or self-hostable deployment of Perplexity Sonar was found on the website.
Private Cloud / data center: unclear
Not specified on the website. No statements were found regarding dedicated customer environments, private cloud, or segregated EU/EEA data centers.
EU SaaS / Managed: partial
There is a clearly documented SaaS/API service. However, EU data residency or EU/EEA operation of the service was not specified on the website.
Hybrid: unclear
Not specified on the website. No hybrid operating models were described.
DPA / Data Processing Agreement: unclear
No DPA or corresponding contractual documentation was found on the website.
No training: covered
The website states for the Sonar API a strict zero-data-retention policy and that no customer data is used to train the models.
Open source / transparency path: partial
A transparent path is only partially recognizable. The website shows integrations and, for the Agent API, refers to third-party models; however, no open, self-hostable model or openly documented core components of Sonar were found.
Data processing
According to the website, the Sonar API processes requests without storing content data and collects only billing-related metadata such as token count, model used, timestamps, duration, and API key identification. External components are also apparent for the platform, such as Stripe for payments and, in the Agent API, third-party models from other providers. No information on EU data residency, subprocessors, or data center locations was found on the website.
Conclusion
From an EU/EEA perspective, Perplexity Sonar is primarily interesting because of the documented zero-data-retention policy and the exclusion of training on customer data. However, several key pieces of evidence for a robust GDPR assessment are missing from the website, particularly regarding a DPA, EU data residency, server locations, and subprocessors. Therefore only 'conditionally'.
Sources
| On-prem / local hosting | ❓ |
| Private cloud / data center | ❓ |
| EU SaaS / Managed | ⚠️ |
| Hybrid | ❓ |
| DPA / AVV | ❓ |
| No training on customer data | ✅ |
| Open source / transparency path | ⚠️ |
On-Prem / local hosting: indirect / not available
No on-premise, local, or self-hostable deployment of Perplexity Sonar was found on the website.
Private Cloud / data center: unclear
Not specified on the website. No statements were found regarding dedicated customer environments, private cloud, or segregated EU/EEA data centers.
EU SaaS / Managed: partial
There is a clearly documented SaaS/API service. However, EU data residency or EU/EEA operation of the service was not specified on the website.
Hybrid: unclear
Not specified on the website. No hybrid operating models were described.
DPA / Data Processing Agreement: unclear
No DPA or corresponding contractual documentation was found on the website.
No training: covered
The website states for the Sonar API a strict zero-data-retention policy and that no customer data is used to train the models.
Open source / transparency path: partial
A transparent path is only partially recognizable. The website shows integrations and, for the Agent API, refers to third-party models; however, no open, self-hostable model or openly documented core components of Sonar were found.
Data processing
According to the website, the Sonar API processes requests without storing content data and collects only billing-related metadata such as token count, model used, timestamps, duration, and API key identification. External components are also apparent for the platform, such as Stripe for payments and, in the Agent API, third-party models from other providers. No information on EU data residency, subprocessors, or data center locations was found on the website.
Conclusion
From an EU/EEA perspective, Perplexity Sonar is primarily interesting because of the documented zero-data-retention policy and the exclusion of training on customer data. However, several key pieces of evidence for a robust GDPR assessment are missing from the website, particularly regarding a DPA, EU data residency, server locations, and subprocessors. Therefore only 'conditionally'.
Sources
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?
For Perplexity Sonar, GDPR-compliant use in the EU/EEA is only conditionally plausible. Positively documented for the Sonar API are a strict zero-data-retention policy and the exclusion of training with customer data. At the same time, no reliable information can be found on the stated website regarding EU/EEA server locations, EU data residency, data center locations, subprocessors, or a DPA/AVV. In addition, the documentation refers to third-party models and external payment processing for parts of the platform, which creates additional review effort from an EU/EEA perspective.
Positive
The website explicitly states that the Sonar API does not store transmitted content data and does not use customer data to train the models. In addition, security attestations such as SOC 2 Type II are mentioned.
Negative
The website does not specify an EU/EEA server location, EU data residency, a DPA/AVV, a list of subprocessors, specific data centers, or on-premise/self-hosting options. For the Agent API, the documentation also mentions the use of third-party providers such as OpenAI, Anthropic, Google, and xAI, which can create additional data protection complexity.
Server location
Not specified on the website. No specific locations of servers or data centers in the EU/EEA were found on the stated domain.
