xAI

Grok 2 Vision

xAI•Documentation

grok-2-vision-1212

xAI's multimodal model with image understanding. Accepts JPEG and PNG images up to 20MB alongside text for richer, context-aware responses.

Use this model with Aisle

Have natural conversations with the model in a familiar interface

Automate tasks, share with your team, and deploy to chat

Test prompt variants, model settings, and compare models side by side

Chain prompts together for complex automation and outcomes

Context Window

33K

tokens

Max Output

32,768

tokens

Temperature

0 – 2

default: 1

Web Search

Available

Structured Output

Available

Supported File Formats

Images

JPEG(20 MB)PNG(20 MB)

Documents

pdftextdocxlsrtfdocxxlsxpptxpptodtodpods

Grok models require documents to be uploaded to xAI's Files API before use in chat. Files are stored for up to 30 days and are not used for model training under xAI's Enterprise API terms. xAI Privacy Policy