Private AI Chat
Sovereign, Secure, and Swiss-hosted AI chat built for teams that need power, privacy and control.
Product Overview
PAI Chat is the conversational interface of Safe Swiss Cloud’s Private AI platform. It lets your organisation work with a curated choice of private LLMs inside a protected environment – fast, reliable and ready for real work.
Teams can securely analyse and summarise documents, run research, brainstorm ideas, write and debug code, explore complex concepts or get learning support – without sending sensitive data to public AI services. PAI Chat structures work into workspaces and threads, supports collaboration across teams, and can optionally enrich results with up-to-date web information.
Key Features
Private LLMs in a secure environment
- Work with multiple private large language models optimised for different use cases (reasoning, coding, multilingual content, etc.).
- All prompts, documents and answers stay inside your Private AI environment – no data is sent to public AI services.
Integrated web search
- Anonymous web search through a “meta” search engine at Safe Swiss Cloud through non-tracking search engines.
- Enable or disable web search per chat.
- Optional: Can be disabled completely for customers (e.g. legal and medical), forcing answers strictly based on internal documents and model knowledge.
Document summaries and analysis
- Upload files (PDFs, Office), markdown, code repositories and more.
- Chat directly “against” your documents to ask questions, extract data and create summaries.
- Vector search and context-aware retrieval ensure answers are based on the most relevant content.
Powerful web-based chat client
- Modern browser-based interface for normal and power users.
- Work is organised in workspaces and threads so projects and topics stay clearly separated.
- Define access, retention and governance rules according to your compliance requirements.
Research & brainstorming
- Analyse and summarise large amounts of text quickly.
- Use PAI Chat to explore ideas, draft concepts and compare options.
- Combine internal knowledge with optional web search for richer insights.
Coding assistant
- Generate code snippets, functions or templates in common programming languages.
- Get help with debugging, refactoring and documenting existing code.
- Use PAI Chat as a secure coding companion for prototypes and automation.Analyse and summarise large amounts of text quickly.
Recommendations & decision support
- Get structured suggestions for solution options, next steps and implementation plans.
- Ask for reading lists, checklists and best-practice approaches to specific problems.
Collaboration & sharing
- Share prompts, answers and threads with colleagues.
- Reuse successful prompts as internal “recipes” for recurring tasks.
- Establish consistent patterns for how your organisation uses AI.
High-quality outputs for text and code
- Produce high-quality drafts for emails, reports, documentation and learning material.
- Generate reliable code suggestions for scripts, integrations and workflow automation.
- Support content creation, coding, teaching and operations in one unified tool.
Ready for Private AI Chat?
In our free briefing, we will show you how to use Private AI Chat productively and securely in the company – without data risks and compliance concerns.
Service Description
PAI Chat is Safe Swiss Cloud’s fully managed Private AI service, giving your team secure, browser-based access to a curated selection of large language models hosted entirely on GPU infrastructure in our Swiss data centres. Each customer receives a dedicated, isolated environment for chat, document analysis and web research — with no logging of prompts or responses, strong authentication, and full Swiss data sovereignty by default.
The following service details describe how PAI Chat is delivered, secured and billed:
- Standard service: SSC provides customers with a web based chat service, allowing customers to “chat” with a selection of LLMs (see the list above). These are usually open source large language models and provided as-is with no warranties.
- Fully Managed: This is a fully managed service – SSC operates, maintains and updates the service.
- Every user has their own workspace, where they have access to their AI chat history and customisations.
- Each customer is allocated a dedicated chat container, which runs the chat software and related services (not the LLM). The chat container accesses the LLMs running on GPUs in SSC’s Swiss data centres.
- User authentication is via a central IAM with two factor authentication (TFA) provided by SSC. Technical options are available to integrate certain types of external authentication systems like Active Directory, Entra, OpenID or LDAP. SSC will implement this on a time and material basis.
- Security: Access to AI services is via https with TFA and optionally through a VPN.
- Local documents on the user’s computer or file server can be uploaded for analysis such as creating summaries (RAG / knowledge base). Document processing is completely isolated for each customer. Documents older than 30 days are deleted automatically, unless a customer requests a longer retention period.
- Web search is integrated into the Chat client and can be be turned on and off as required. The web search is proxied by SSC to prevent tracking.
- Web sites and documents on the web can be downloaded and analysed.
- IAM with TFA: The default IAM is fully managed and hosted by SSC.
- NO LOGGING of prompts and replies from the LLM. Only meta data is logged e.g. when a request was made, which model was used, how long it took to completion and how many tokens were used.
- The PAI Chat client does maintain a history of prompts and answers in encrypted form within the dedicated container instance of each customer. This is to allow customers to see their history and reuse it in the user Chat interface.
- Charging: monthly per user seat plus local document storage space.
LLM Models at Safe Swiss Cloud: Core Characteristics
Choose from a rich catalog of sovereign LLMs – all with the same strict privacy and compliance guarantees. Safe Swiss Cloud’s Private AI (PAI) services combine a broad selection of open-source LLMs with a consistent security, privacy and compliance foundation. You keep full control over data, infrastructure and model choice, while we provide the sovereign hosting and operational excellence
Which LLM Models are supported by PAI?
SSC provides access to the following open source large language models. These are provided as-is with no warranties:
| Model | Type | Details |
| apertus-70b | Chat | Optimized for multilingual dialogue use cases. |
| bge-m3 | Embedding | Optimized for Embeddings and parse retrieval with support for Multi-Functionality, Multilinguality, and Multi-Granularity. |
| bge-reranker-v2 | Reranker | Optimized for Reranker to get relevance score. |
| deepseekr-v32 | Chat | Optimised for reasoning chat completions |
| deepseek-ocr | OCR | Optical Character Recognition |
| gemma-12b-it | Multimodal | Optimized for handling text and image input and generating text output. |
| gemma4-31b | Multimodal | Optimized for handling text and image input and generating text output. |
| gpt-oss-120b | Chat | Optimized for powerful reasoning, agentic tasks, and versatile developer use cases. |
| granite-33-8b | Chat | Optimized for Reasoning and instruction-following capabilities. |
| granite-emb-278m | Embedding | Optimized for Embeddings. |
| granite-vision-2b | Multimodal | Optimized for compact and efficient vision-language model |
| llama4-maverick | Chat and multimodal | Optimized for text and multimodal experiences. |
| llama4-scout-17b | Chat and multimodal | Optimized for text and multimodal experiences. |
| mistral-v03-7b | Chat only | Optimized for multilingual dialogue use cases. |
| qwen3-8b | Reasoning | Optimized for thinking and reasoning. |
| qwq-32b | Reasoning | Optimized for thinking and reasoning. |
| qwen3-vi-235b | Multimodal | Optimized for text and multimodal experiences. |
| whisper-large-v3 | Speech to Text | For converting speech to text. |
Other commercial or proprietary LLMs can also be integrated depending on licensing and infrastructure requirements.
Characteristics of all Private AI Services
Private AI (PAI) involves SSC providing Customers with sovereign Private AI solutions. The following service characteristics apply to all of Safe Swiss Cloud‘s PAI services.
- Multi-lingual LLMs provide you access to knowledge from any language with results being delivered in your own language.
- Choice of models: Select from a large catalogue of open large language models (LLMs) including DeepSeek, Llama4-Maverick, Apertus, Mistral and many more.
- Sovereign AI by design: All LLMs are privately hosted in Switzerland, by Swiss owned entities. Your data always stays under your control. Your data is processed strictly in accordance with Swiss and privacy regulatio
- Privacy: Your data is processed strictly in accordance with with the Swiss Data Privacy Act (DSG) and EU GDPR.
- No Training, Retraining or Fine Tuning of the LLMs with your data.
- ISO Certifications: 27001, 27017, 27018.
- Conforms to the C5 and NIS2 standards
- 100% hosted in Swiss data centers under Swiss control.
Why Private AI?
Sovereignty matters
Public AI is useful—but it can conflict with enterprise privacy, compliance and change control. Private AI keeps prompts, data and outputs inside your perimeter, with model versions you govern.
AI systems hosted by US-controlled providers fall under the US CLOUD Act, even when infrastructure is outside the US. That exposure conflicts with Swiss/EU data-protection expectations. Hosting in Swiss sovereign infrastructure under Swiss control avoids this risk.
Safe Swiss Cloud commitments
- Full privacy: Data is used strictly to provide the contracted service—no training on your proprietary data unless you opt in.
- Hosted by Safe Swiss Cloud in Swiss data centres.
- Swiss law & control: Services run under Swiss law (aligned with EU law); all service entities are Swiss-controlled.
- Not subject to US CLOUD Act coercion: As a fully Swiss-controlled IT group, Safe Swiss Cloud cannot be compelled to disclose customer data by US law.
Outcome: predictable operations, regulatory alignment (GDPR, DSG, FINMA, DORA) and audit-ready AI.
PAI Chat Pricing
This web based Chatbot is for use by end users to chat with one of the available Large Language Models.
There is an option to allow the LLM to access the Internet so that it can answer questions with current Internet data. This option can optionally be blocked.
| Service | Description | Units | Price in CHF / EUR |
|---|---|---|---|
| PAI Chat | Chatbot with advanced functionality, including single sign on (SSO), a selection of LLMs – large language models – many with 70 billion parameters or more, document and image uploading for analysis and summaries, chat histories etc.* | Per user / month (on demand) Per user / month (annual) | 35.00 30.00 |
| Web Search | An anonymous web search is provided with the client. A “meta search” server at Safe Swiss Cloud ensures that the web search requests cannot be traced back to the actual user. This search server uses non-tracking web search services like DuckDuckGo, Startpage, Wikipedia etc. Users can turn the web search on and off for each request in the PAI Chat client. This function can be completely disabled for a customer if desired. | Number of requests | No charge |
How to get started
- Initial briefing – We assess your goals, compliance requirements, and current IT landscape to determine the optimal AI architecture.
- Architecture design – Together we select suitable LLMs, integration points, and hosting options that fit your strategy.
- Implementation – We deploy and integrate the AI environment, connecting it to your internal systems securely and efficiently.
FAQ
Questions and answers about Private AI by Safe Swiss Cloud
Private AI at Safe Swiss Cloud means three things:
- Customer data — prompts, replies, and AI output — is never used to train models.
- Customer data is handled in accordance with the Swiss Data Protection Act (DSG) and the EU’s GDPR, ensuring full privacy compliance.
- The infrastructure is sovereign, meaning it is not subject to arbitrary service interruptions for non-technical reasons.
Safe Swiss Cloud’s Private AI complies fully with the revised Swiss Data Protection Act (CH DSG) and the EU GDPR.
No. Prompts and responses are not stored in logs and therefore cannot be viewed or traced by Safe Swiss Cloud staff.
Yes. Every customer receives their own dedicated front end and RAG (Retrieval-Augmented Generation) system. Prompts are fully isolated from one another and have no cross-customer side effects.
Yes. This option is more expensive because it involves dedicated GPUs for a single customer. It is a viable solution for customers with sufficient workload volume and strict compliance requirements for a dedicated AI infrastructure.
Swiss law requires that Safe Swiss Cloud may only hand over customer data to non-Swiss or foreign governments if a warrant issued by a Swiss court under Swiss law has been served. This provides a robust legal barrier against extraterritorial data access requests.
Yes. The technical privacy features, together with the regulatory frameworks of the Swiss Data Protection Act and the EU GDPR, ensure that the Private AI environment is suitable for regulated data, including healthcare and financial data.
Yes. Safe Swiss Cloud offers dedicated GPU and storage clusters for individual customers.
Backups are always encrypted. Snapshots of an encrypted volume are also encrypted. Customers can additionally choose to encrypt data at rest, which ensures that all snapshots remain encrypted and cannot be used in any way other than intended.
We use open-source models accessible via the industry-standard OpenAI API. This allows customers to switch models and providers as needed, without being locked into proprietary formats or interfaces.
All AI data and models are stored and processed exclusively in Switzerland.
Safe Swiss Cloud uses open-source models and does not train — or contribute to training — these models. As a result, customer data (prompts, AI output, logs, etc.) is never used for any purpose other than what the customer explicitly requests. This prevents confidential information from inadvertently entering the public domain.
Many publicly available AI services silently use customer data for training. For example, an employee who uploads a file containing confidential information to a public AI service may see that data incorporated into a future large language model (LLM) iteration — potentially enabling a competitor to retrieve proprietary information in a future query.
Safe Swiss Cloud offers an SLA with 99.9% uptime. For paid support plans, the guaranteed response time is a maximum of one hour.
We offer services to develop MCP (Model Context Protocol) servers for connecting AI systems to enterprise data sources and workflows.
Safe Swiss Cloud offers paid support packages with 24/7 coverage. For details, please visit our Support Services page.
Safe Swiss Cloud is ISO 27001, ISO 27017, and ISO 27018 certified and audited annually. This ensures that an Information Security Management System (ISMS) is in place, that the necessary standards for protecting Personally Identifiable Information (PII) are met, and that additional security and privacy measures for cloud environments are implemented.
Safe Swiss Cloud also complies with a range of industry-specific standards, including FINMA and BaFin (finance), HIPAA and FMH (healthcare), EU GDPR and Swiss DSG (data protection), as well as C5 and NIS2.
Large Language Models are accessed via the industry-standard OpenAI API. Interfaces to enterprise data are based on the Model Context Protocol (MCP) standard. Together, these ensure a very high degree of interoperability between systems, making it straightforward to switch models or providers.
Like all AI service providers — including the major international public cloud providers — Safe Swiss Cloud does not guarantee specific performance levels for AI workloads. However, a large pool of high-performance GPUs and dynamic capacity management have been implemented to ensure strong performance under normal operating conditions.
