Choosing the Right Model
The right model depends on your task, compliance needs, and budget. All Schatzi AI models run exclusively on Swiss infrastructure, so your data never leaves Switzerland.
Quick Decision Guide
"I just want to draft an email or a message"
→ Apertus Swiss LLM - Large
"I need Swiss/EU compliance and transparency"
→ Apertus Swiss LLM - Large
"I need complex reasoning and agent workflows"
→ Chat & Document Analysis & Reasoning - Large
"I need up-to-date web search and current information"
→ Search, Chat & Analysis - Small
"I need to analyse documents and images"
→ Chat & Document Analysis & Reasoning - Large
"I need maximum capability across everything"
→ Chat & Document Analysis & Reasoning - Large
Model Capabilities at a Glance
API-only models are accessible via the REST API but are not visible in the Chat UI.
| Model | Category | Vision | Reasoning | Web Search | Function Calling | Context Window | Availability |
|---|---|---|---|---|---|---|---|
| Apertus Swiss LLM - Large | Swiss LLM (AI Act Compliant) | No | No | No | No | 65,536 | Chat UI & API |
| Chat & Document Analysis & Reasoning - Large | Reasoning & Problem-Solving | Yes | Yes | No | Yes | Not specified | API only |
| Document Analysis - Small | Vision & Document Analysis | Yes | No | No | Yes | 32,768 | API only |
| Document Analysis - Xtra Small | Vision & Document Analysis | Yes | No | No | No | 16,384 | API only |
| Fast Reasoning & Instruction Following - Small | Reasoning & Problem-Solving | No | No | No | Yes | 32,768 | API only |
| Reasoning & Problem Solving - Small | Reasoning & Problem-Solving | No | Yes | No | Yes | 32,768 | API only |
| Llama 4 Maverick multi modal - Small | Vision & Document Analysis | Yes | No | No | Yes | 32,768 | API only |
| Reasoning & Agent tasks - Large | Reasoning & Problem-Solving | No | Yes | No | Yes | 65,536 | API only |
| Reasoning & Problem Solving - Medium | Reasoning & Problem-Solving | No | Yes | No | Yes | 32,768 | API only |
| Reasoning & Problem Solving - Xtra Large | Reasoning & Problem-Solving | No | No | No | No | Not specified | API only |
| Reasoning & Tool Use - Large (GLM-4.5 Air) | Reasoning & Problem-Solving | No | Yes | No | Yes | 131,072 | API only |
| Search, Chat & Analysis - Small | Chat & General Purpose | Yes | No | Yes | No | Not specified | API only |
| Chat, Document Analysis & Agent tasks - Xtra Large | Reasoning & Problem-Solving | Yes | Yes | Yes | Yes | 250,000 | Chat UI & API |
| Document Analysis & OCR - Small (DeepSeek OCR) | Vision & Document Analysis | Yes | No | No | No | 8,192 | API only |
| Chat, Multi-lingual, Coding & function calling - Small | Multilingual | No | No | No | Yes | 128,000 | Chat UI & API |
| Chat, Document Analysis, Coding & Reasoning - Xtra Large | Reasoning & Problem-Solving | Yes | Yes | No | Yes | 1,000,000 | Chat UI & API |
| Chat, Vision, Document Analysis & Reasoning - Medium | Reasoning & Problem-Solving | Yes | Yes | No | Yes | 256,000 | Chat UI & API |
| inference-miner-u25 | Vision & Document Analysis | No | No | No | No | Not specified | API only |
| Reasoning & Tool Use - Xtra Large (GLM-5.2) | Reasoning & Problem-Solving | No | Yes | No | Yes | Not specified | Chat UI & API |
| Apertus Swiss LLM - Large (v1.5) | Swiss LLM (AI Act Compliant) | No | No | No | No | 65,536 | API only |
Pricing Overview
Loading prices...
Pricing is subject to change at our discretion.
For how tokens are calculated and billed, see Understanding Tokens.
General Tips
Start Simple
Begin with a cost-effective model such as Apertus Swiss LLM - Large for routine tasks, and move to a more capable model when you need vision or reasoning. See the Lite Plan for entry-level access.
Match Compliance Requirements
For strict data sovereignty and AI Act compliance, Apertus Swiss LLM - Large is the recommended choice. Learn more about our Data Protection standards.
Consider Context Window
Match the model's context window to your document length — longer documents need a larger context window.
When to Upgrade / Downgrade
- Upgrade to Chat & Document Analysis & Reasoning - Large or Chat & Document Analysis & Reasoning - Large when a task needs deeper reasoning, agent workflows, or multi-modal capability.
- Downgrade to Apertus Swiss LLM - Large for routine chat and drafting to optimise for speed and cost.
Most users find 2–3 models cover 90% of their needs — typically Apertus Swiss LLM - Large for quick tasks, Chat & Document Analysis & Reasoning - Large for specialised work, and Apertus Swiss LLM - Large for compliance-sensitive operations. Monitor usage in the dashboard to optimise over time.