Model Comparison
Schatzi AI provides access to 6 active state-of-the-art AI models. All models run exclusively on Swiss infrastructure, ensuring your data never leaves Switzerland and remains fully compliant with Swiss data protection regulations.
This guide helps you choose the right model for your specific needs, understand pricing, and optimize costs while maintaining complete data sovereignty.
Complete Model Reference
Swiss LLM (AI Act Compliant)
Apertus Swiss LLM - Large
- Context Window: 65,536 tokens (~49,000 words)
- Streaming: Supported
Capabilities:
- Data and methods documented for unprecedented transparency
- Fully compliant with the AI Act and respectful of privacy and intellectual property
- 70B parameter model delivering frontier-level performance
- Ideal for multilingual services, government agencies, and R&D teams
- Reliable and adaptable for sensitive applications
Pricing:
- Input: ... per million tokens
- Output: ... per million tokens
Best For:
- Government agencies requiring compliance
- Teams requiring full transparency
- Multilingual European services
- AI Act compliance-critical applications
Chat & General Purpose
Chat & Document Analysis - Medium
- Context Window: 128,000 tokens (~96,000 words)
- Streaming: Supported
Capabilities:
- Versatile multimodal model for document analysis and conversational agents
- Instant responses with strong contextual understanding
- Efficient support for all major European languages
- Optimized for chat and document processing workflows
Pricing:
- Input: ... per million tokens
- Output: ... per million tokens
Best For:
- Daily business communications
- Email drafting and responses
- General document analysis
- Customer service responses
- Quick content generation
Search, Chat & Analysis - Small
- Context Window: Variable
- Vision: Supported
- Streaming: Supported
Capabilities:
- Optimized for web search and chat applications
- Suitable for artists and content creation, including storytelling
- Vision capabilities for image analysis and visual content processing
- Efficient for creative and research tasks
Pricing:
- Input: ... per million tokens
- Output: ... per million tokens
Best For:
- Web search and research tasks
- Content creation and storytelling
- Visual content analysis
- Quick information retrieval
- Creative applications
Chat & Document Analysis - Large
- Context Window: Variable
- Vision: Supported
- Streaming: Supported
Capabilities:
- Large-scale model delivering frontier-level performance across complex tasks
- Advanced multilingual capabilities
- Reasoning mode can be enabled to dynamically tailor responses to context and complexity
- Vision capabilities for comprehensive document analysis
Pricing:
- Input: ... per million tokens
- Output: ... per million tokens
Best For:
- Complex document analysis
- High-quality content generation
- Advanced multilingual tasks
- Tasks requiring frontier-level performance
- Dynamic reasoning tasks
Reasoning & Problem-Solving
Reasoning & Agent tasks - Large
- Context Window: 32,768 tokens (~24,500 words)
- Function Calling: Supported
- Reasoning: Supported
- Streaming: Supported
Capabilities:
- Optimized for powerful reasoning and agentic tasks
- Function calling support for versatile developer use cases
- Advanced problem-solving capabilities
- Structured thinking and logical analysis
Pricing:
- Input: ... per million tokens
- Output: ... per million tokens
Best For:
- Complex strategic analysis
- Multi-step problem decomposition
- Agentic workflows and automation
- Technical architecture decisions
- Advanced reasoning tasks
Chat, Document Analysis & Agent tasks - Xtra Large
- Context Window: Variable
- Vision: Supported
- Function Calling: Supported
- Reasoning: Supported
- Streaming: Supported
Capabilities:
- Very large-scale model delivering frontier-level performance across complex tasks
- Advanced multilingual capabilities
- Reasoning mode can be enabled to dynamically tailor responses to context and complexity
- Optimized for powerful reasoning, agentic tasks, and versatile developer use cases
- Comprehensive vision and document analysis capabilities
Pricing:
- Input: ... per million tokens
- Output: ... per million tokens
Best For:
- Most demanding reasoning and analysis tasks
- Complex agentic workflows
- Comprehensive document analysis with reasoning
- High-stakes business decisions
- Advanced multilingual agent applications
This is our most comprehensive model. Use for complex reasoning and agent tasks where the capabilities justify the higher cost.
Complete Pricing Overview
Loading prices...
Cost Estimation
Typical Task Types
| Task Type | Token Usage | Recommended Model |
|---|---|---|
| Email response | 500 input + 300 output | Chat & Document Analysis - Medium |
| 10-page document summary | 10K input + 1K output | Chat & Document Analysis - Medium |
| Contract analysis (30 pages) | 30K input + 2K output | Apertus Swiss LLM - Large |
| Complex reasoning task | 5K input + 3K output | Reasoning & Agent tasks - Large |
| Multilingual exchange | 15K input + 10K output | Chat, Document Analysis & Agent tasks - Xtra Large |
Choose the right model for each task. Use smaller, cheaper models for routine work and reserve premium models for complex analysis. See the pricing table above for current rates.
Model Availability
Currently Active Models
- Apertus Swiss LLM - Large
- Chat & Document Analysis - Medium
- Chat & Document Analysis - Large
- Search, Chat & Analysis - Small
- Reasoning & Agent tasks - Large
- Chat, Document Analysis & Agent tasks - Xtra Large
We regularly evaluate and update our model offerings. Check your dashboard for the latest available models and current pricing.
Related Documentation
- Model Profiles - Detailed technical specifications
- Choosing the Right Model - Interactive decision guide
- Understanding Tokens - How billing works
- Prompt Engineering - Get better results
FAQ
Q: Can I switch models mid-conversation? A: Yes! You can change models at any time. The conversation context carries over (note: very long contexts may be truncated for models with smaller context windows).
Q: Which model is best for Swiss legal documents? A: Apertus Swiss LLM - Large is specifically designed for this use case. It is AI Act compliant, fully documented, and optimized for Swiss multilingual requirements while ensuring your data never leaves Switzerland.
Q: What's the cheapest way to process 100 documents? A: Use Chat & Document Analysis - Medium for routine processing, or Search, Chat & Analysis - Small for simpler tasks. Reserve Apertus Swiss LLM - Large or Chat & Document Analysis - Large for complex analysis requiring compliance or advanced capabilities.
Q: Do all models support document upload? A: Yes, all active models support document analysis. Models with vision capabilities (Search, Chat & Analysis - Small, Chat & Document Analysis - Large, and Chat, Document Analysis & Agent tasks - Xtra Large) can also analyze images and visual content within documents.
Q: How do I track which model costs what? A: Your usage dashboard shows token usage and costs broken down by model. Navigate to Account → Usage & Billing to monitor consumption per model.
Q: Can I set spending limits per model? A: Currently, you can set overall monthly spending limits at the account level. Model-specific spending controls are on our roadmap.
Get Started
Ready to choose your model?
- Log in to your Schatzi AI account
- Start a new chat in the interface
- Click the model selector at the top of the chat
- Choose the appropriate model for your task based on this guide
- Start chatting with full Swiss data sovereignty
Need help? Contact Support | View Pricing Plans
NOTE Pricing is subject to change at our discretion.