Pixtral Large

Processes multiple images (minimum 30 high-resolution images documented to fit within 128K context) interleaved with text prompts in a single conversation, using a dedicated 1B-parameter vision encoder that tokenizes visual input alongside text tokens. The architecture maintains Mistral Large 2's text foundation while extending the attention mechanism to handle mixed modality sequences, enabling coherent reasoning across image-text pairs without requiring separate API calls per image.

Analyzes scanned documents, PDFs, and forms by extracting text and visual layout information through the vision encoder, then answering natural language questions about document content, structure, and relationships. The model combines OCR-level text extraction with spatial reasoning about document layout, enabling it to locate and reason about specific information within complex multi-page or multi-section documents.

Processes documents and images containing text in multiple languages, with demonstrated support for Swiss German and French. Vision encoder extracts text regardless of language, and language decoder applies multilingual understanding to answer questions and extract information. Specific language support list not documented, but multilingual OCR capability confirmed through receipt processing examples.

Interprets charts, graphs, tables, and other data visualizations by analyzing visual elements (axes, legends, data points, trends) and answering questions about data relationships, trends, and specific values. The vision encoder extracts visual structure while the language model reasons about the underlying data semantics, enabling both factual queries ('what is the value at X') and analytical questions ('what trend does this show').

Extracts text from images across multiple languages (documented with Swiss German example) while simultaneously reasoning about extracted content, context, and relationships. Unlike traditional OCR engines that output raw text, this capability integrates text extraction with language understanding, enabling the model to correct OCR errors, understand context-dependent meaning, and answer questions about extracted text in a single pass.

Solves mathematical problems presented in visual form (equations in images, mathematical diagrams, geometry problems, word problems with visual context) by combining visual understanding with mathematical reasoning. The model achieves 69.4% on MathVista benchmark, outperforming all tested alternatives, through integrated visual parsing and symbolic/numerical reasoning without requiring separate math engines.

Integrates visual understanding with tool-use capabilities, enabling the model to analyze images and invoke external functions or APIs based on visual content understanding. The model can interpret visual data, extract relevant parameters from images, and call appropriate tools with image-derived context, supporting workflows where visual analysis triggers downstream automation.

Maintains full text-only language capabilities from Mistral Large 2 foundation model without documented performance degradation, supporting general language understanding, reasoning, and generation tasks. The 124B architecture extends Mistral Large 2 with vision capabilities while preserving text-only performance, enabling the model to handle pure text tasks alongside multimodal inputs in the same conversation.

Distributes model weights via HuggingFace (referenced as 'Mistral Large 24.11') enabling local deployment without API dependency, subject to Mistral Research License (research/educational) or Mistral Commercial License (production). The open-weights distribution enables organizations to run inference on their own infrastructure, avoiding cloud API latency and data transmission, though specific deployment formats (GGUF, safetensors, etc.) and hardware requirements are not documented.

Supports 128K token context window accommodating both text and image tokens, with documented capacity for minimum 30 high-resolution images alongside text. The context window is shared between images (which consume multiple tokens per image depending on resolution) and text, enabling long-form conversations with multiple images without context resets, though actual maximum image count depends on image resolution and text length.

Supports 128K token context window enabling extended conversations with multiple images and long text passages. Context window is shared between image tokens (approximately 4.3K tokens per high-resolution image) and text tokens, allowing up to 30 high-resolution images or proportionally more text. Enables multi-turn conversations where previous context is maintained across turns without re-uploading images.