Skip to main content

Model Profiles

Schatzi AI hosts all models exclusively on Swiss infrastructure, ensuring your data never leaves Switzerland. This page provides detailed technical specifications, capabilities, and pricing for each available model to help you select the optimal solution for your business requirements.

For guidance on selecting the right model for your use case, see /ai-models/choosing-model. To understand how token pricing works, visit /subscription-billing/understanding-tokens.

Apertus Swiss LLM - Large​

Description​

Designed for organizations requiring maximum transparency and regulatory compliance, this 70B parameter model serves as a reliable foundation for multilingual services, government applications, and research initiatives. With fully documented training methodologies and strict adherence to AI Act requirements, it prioritizes data privacy and intellectual property protection while delivering market-leading performance.

Specifications​

  • Context window: 65,536 tokens
  • Max output tokens: Not specified
  • Vision support: No
  • Reasoning mode: No
  • Function calling: No
  • Streaming: Yes

Ideal Use Cases​

  • Government service automation and citizen support
  • Regulatory compliance documentation and reporting
  • Academic research and R&D documentation analysis
  • Multilingual public sector chatbots
  • Legal document review with transparency requirements
  • Cross-border administrative processes

Strengths​

  • Complete training transparency and methodology documentation
  • Full AI Act compliance for regulated industries
  • Robust multilingual capabilities for European languages
  • 70B parameter scale delivering high performance
  • Guaranteed Swiss data sovereignty

Limitations​

  • No vision or image analysis capabilities
  • No function calling support for tool integration
  • Higher per-token cost compared to smaller alternatives

Pricing​

  • Input: ... per million tokens
  • Output: ... per million tokens

When to Use​

Choose this model when regulatory compliance, training transparency, and data sovereignty are non-negotiable requirements. It is specifically engineered for government agencies, research institutions, and organizations handling sensitive information that must remain within Swiss jurisdiction while maintaining full auditability of AI decision-making processes.

When to Choose a Different Model​

For applications requiring vision capabilities or image analysis, use Chat & Document Analysis - Large or Chat, Document Analysis & Agent tasks - Xtra Large. If your workflow requires function calling or autonomous agent capabilities, select Reasoning & Agent tasks - Large or Chat, Document Analysis & Agent tasks - Xtra Large instead.

Chat & Document Analysis - Medium​

Description​

A versatile workhorse designed for rapid document processing and conversational applications. This model delivers instant responses with robust contextual understanding across all major European languages, making it ideal for businesses operating in multilingual environments that require efficient text processing without unnecessary complexity.

Specifications​

  • Context window: 128,000 tokens
  • Max output tokens: Not specified
  • Vision support: No
  • Reasoning mode: No
  • Function calling: No
  • Streaming: Yes

Ideal Use Cases​

  • High-volume document processing and summarization
  • Multilingual customer support automation
  • Content localization and translation workflows
  • Internal knowledge base queries and retrieval
  • Batch report analysis and extraction
  • Email drafting and business correspondence

Strengths​

  • Extensive 128K context window for large documents
  • Highly cost-effective pricing structure
  • Fast response times with streaming support
  • Comprehensive European language coverage
  • Reliable performance for text-centric workflows

Limitations​

  • No vision or multimodal capabilities
  • No function calling for external tool integration
  • Not optimized for complex multi-step reasoning

Pricing​

  • Input: ... per million tokens
  • Output: ... per million tokens

When to Use​

Deploy this model for processing large documents or high-volume text analysis where cost efficiency and speed matter more than advanced reasoning or multimodal capabilities. It excels at straightforward document analysis, chat applications, and any workflow where the 128K context window can accommodate entire reports or extensive conversation histories.

When to Choose a Different Model​

For vision requirements or image-rich document processing, select Search, Chat & Analysis - Small or Chat & Document Analysis - Large. For agentic workflows requiring function calling or complex reasoning, choose Reasoning & Agent tasks - Large or Chat, Document Analysis & Agent tasks - Xtra Large.

Reasoning & Agent tasks - Large​

Description​

Engineered for sophisticated analytical workflows and autonomous agent applications. This model excels at complex problem-solving, logical inference, and structured tool use, making it the preferred choice for developers building intelligent automation systems that require step-by-step reasoning capabilities.

Specifications​

  • Context window: 32,768 tokens
  • Max output tokens: Not specified
  • Vision support: No
  • Reasoning mode: Yes
  • Function calling: Yes
  • Streaming: Yes

Ideal Use Cases​

  • Autonomous agent development and deployment
  • Complex data analysis and business logic automation
  • Multi-step reasoning and decision support systems
  • API integration and external tool orchestration
  • Workflow automation requiring structured thinking
  • Technical problem-solving and debugging assistance

Strengths​

  • Native reasoning capabilities for complex analysis
  • Full function calling support for tool integration
  • Developer-friendly architecture for agent building
  • Strong analytical performance with streaming
  • Optimized for agentic task completion

Limitations​

  • No vision support for image analysis
  • Smaller context window (32K) compared to document-focused models
  • May be excessive for simple chat-only applications

Pricing​

  • Input: ... per million tokens
  • Output: ... per million tokens

When to Use​

Select this model when building AI agents, automation workflows, or applications requiring structured reasoning and external tool integration. It is specifically designed for scenarios where the model must break down complex problems, reason through multiple steps, and interact with external systems via function calls.

When to Choose a Different Model​

For vision-enabled applications or image analysis, use Chat & Document Analysis - Large or Chat, Document Analysis & Agent tasks - Xtra Large. For simpler chat interactions without reasoning requirements, Chat & Document Analysis - Medium offers better cost efficiency and a larger context window.

Search, Chat & Analysis - Small​

Description​

A compact yet capable multimodal model optimized for creative applications and web-enabled research. Combining vision capabilities with conversational fluency, it serves content creators and researchers who need to analyze visual content alongside text, while maintaining the agility required for interactive storytelling and artistic projects.

Specifications​

  • Context window: Not specified
  • Max output tokens: Not specified
  • Vision support: Yes
  • Reasoning mode: No
  • Function calling: No
  • Streaming: Yes

Ideal Use Cases​

  • Visual content analysis and image description
  • Creative storytelling and narrative development
  • Web research with visual source analysis
  • Artistic project support and inspiration
  • Image-based documentation review
  • Content creation workflows combining text and visuals

Strengths​

  • Vision capabilities for image analysis and description
  • Optimized for creative and artistic tasks
  • Web search integration for current information
  • Fast streaming responses for interactive use
  • Balanced performance for small-scale applications

Limitations​

  • No function calling support for tool integration
  • No dedicated reasoning mode for complex analysis
  • Context window specifications not defined

Pricing​

  • Input: ... per million tokens
  • Output: ... per million tokens

When to Use​

Choose this model for creative projects requiring image analysis, storytelling, or when combining visual and textual content generation. It is particularly well-suited for marketing teams, content creators, and researchers who need to analyze visual assets while maintaining conversational fluidity.

When to Choose a Different Model​

For complex agent tasks requiring function calling or advanced reasoning, use Reasoning & Agent tasks - Large or Chat, Document Analysis & Agent tasks - Xtra Large. For large-scale document processing with defined context requirements, Chat & Document Analysis - Medium offers a specified 128K context window.

Chat & Document Analysis - Large​

Description​

A large-scale solution delivering frontier-level performance across complex enterprise tasks. With advanced multilingual capabilities and vision support, it adapts dynamically to query complexity while handling extensive documents and visual content with precision, making it suitable for high-stakes business applications.

Specifications​

  • Context window: Not specified
  • Max output tokens: Not specified
  • Vision support: Yes
  • Reasoning mode: No
  • Function calling: No
  • Streaming: Yes

Ideal Use Cases​

  • Enterprise document analysis with visual elements
  • Complex multilingual projects and localization
  • High-stakes content review and validation
  • Large-scale report generation with charts and graphs
  • Image-rich documentation analysis
  • Advanced customer support with visual troubleshooting

Strengths​

  • Vision capabilities for comprehensive document analysis
  • Advanced multilingual support for global operations
  • Frontier-level performance on complex tasks
  • Handles mixed visual and textual content
  • Reliable streaming for real-time applications

Limitations​

  • No function calling capability for external integrations
  • No dedicated reasoning mode for step-by-step analysis
  • Premium pricing tier compared to medium alternatives

Pricing​

  • Input: ... per million tokens
  • Output: ... per million tokens

When to Use​

Deploy this model for complex document analysis requiring vision capabilities, especially when handling image-rich documents, scanned materials, or requiring top-tier multilingual performance. It bridges the gap between pure text models and full agent systems, offering visual understanding without the complexity of function calling.

When to Choose a Different Model​

For agent-based workflows requiring function calling or reasoning, select Chat, Document Analysis & Agent tasks - Xtra Large. For cost-effective high-volume text processing without vision requirements, Chat & Document Analysis - Medium offers superior value with a defined 128K context window.

Chat, Document Analysis & Agent tasks - Xtra Large​

Description​

Our most capable model, designed for the most demanding enterprise applications. This very large-scale system combines vision, reasoning, and agentic capabilities with advanced multilingual support, enabling sophisticated automation across complex document workflows, analytical tasks, and integrated search operations.

Specifications​

  • Context window: Not specified
  • Max output tokens: Not specified
  • Vision support: Yes
  • Reasoning mode: Yes
  • Function calling: Yes
  • Streaming: Yes

Ideal Use Cases​

  • End-to-end enterprise automation pipelines
  • Complex agent orchestration with visual inputs
  • Vision-enabled document analysis and extraction
  • Advanced reasoning workflows with tool use
  • Multilingual agent deployment at scale
  • Integrated search, analysis, and action systems

Strengths​

  • Comprehensive capability set combining vision, reasoning, and function calling
  • State-of-the-art performance across all modalities
  • Advanced multilingual support for global deployment
  • Full agentic functionality for autonomous operations
  • Enterprise-grade reliability and streaming performance

Limitations​

  • Highest cost per token in the portfolio
  • May be excessive for simple or single-purpose tasks
  • Resource intensive for basic applications

Pricing​

  • Input: ... per million tokens
  • Output: ... per million tokens

When to Use​

Select this model for mission-critical applications requiring the full spectrum of AI capabilities—vision, reasoning, and tool use—in a single integrated solution. It is specifically engineered for enterprises building sophisticated automation systems that must process visual documents, reason through complex scenarios, and execute actions via function calls.

When to Choose a Different Model​

For cost-sensitive applications not requiring all capabilities, consider Chat & Document Analysis - Large for vision without function calling, or Reasoning & Agent tasks - Large for reasoning and function calling without vision. For pure text processing, Chat & Document Analysis - Medium provides excellent value.

Model Updates

Model capabilities, context windows, and pricing are subject to change as we continuously improve our Swiss-hosted infrastructure. For the latest specifications and availability, refer to the model comparison page or check your usage dashboard.