Grok 2 Vision
A multimodal model that processes documents, diagrams, charts, screenshots, and photographs.
Input
Output
Context
33K
Max Output
33K
Parameters
—
Technical Specifications
Model TypeChat
Context Window33K
Max Output Tokens33K
Parameters—
Training Cutoff—
Licenseproprietary
Capabilities
Input Modalities
textimage
Output Modalities
text
Features
'structured_outputs']['function_calling'image_understandingvision
Resources & Links
proprietary — Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.