← Back to AI Models

Grok Vision

Multimodal Grok model with advanced image and document understanding

Overview

Multimodal Grok model with advanced image and document understanding

Key Capabilities

  • Vision — suited for tasks requiring vision proficiency
  • Code Generation — suited for tasks requiring code generation proficiency
  • Document Analysis — suited for tasks requiring document analysis proficiency
  • Diagram Understanding — suited for tasks requiring diagram understanding proficiency

Recommended Use Cases

  • Architecture Diagram Analysis
  • Visual Documentation
  • Legacy Document Parsing

Technical Specifications

  • Context Window: 128K tokens
  • Max Output Tokens: 16K tokens
  • Open Weight: No
  • Release Date: August 01, 2025

Pricing

$3/M input tokens, $12/M output tokens

Provider

Grok Vision is developed by xAI. For the latest information, visit the official documentation.