Pixtral Large
Pixtral Large is Mistral's flagship multimodal model, combining powerful text reasoning with state-of-the-art vision capabilities. It can process high-resolution images, charts, diagrams, and documents alongside text, making it a versatile tool for applications that need to understand visual content in context.
Pixtral Large excels at complex visual reasoning tasks — interpreting data visualizations, extracting information from scanned documents, analyzing screenshots, and answering detailed questions about images. Its 128K context window allows processing multiple images alongside extensive text instructions in a single request.
Key Features
High-resolution image understanding with fine-grained detail recognition
Chart, graph, and data visualization interpretation and analysis
Multi-image processing — compare and analyze multiple visuals in one request
128K token context for combining extensive text with visual inputs
OCR-quality text extraction from documents, receipts, and screenshots
Strong spatial reasoning for layout and design analysis
Ideal Use Cases
Automated document processing — invoices, receipts, contracts with visual elements
Data visualization interpretation for business intelligence dashboards
Visual quality assurance and UI screenshot analysis
Medical image annotation and radiology report assistance
Example Prompts for Pixtral Large
Technical Specifications
| Context Window | 128K tokens |
| Modality | Text, Image → Text |
| Provider | Mistral |
| Category | Text Generation |
| Vision | High-resolution, multi-image |
| Max Output | 16K tokens |
| Best For | Complex visual reasoning |
Frequently Asked Questions
Try Pixtral Large now
Start using Pixtral Large instantly — 100 free credits, no credit card required. Access 750+ AI models through one platform.