{"slug":"google/vit-base-patch16-384","title":"ViT Base (Patch 16, 384 resolution)","description":"A base Vision Transformer model with 16x16 patch size and 384x384 input resolution for image classification.","provider":"google","model_type":"vision","status":"active","context_window":null,"max_output_tokens":null,"pricing":null,"modalities":["image"],"capabilities":["vision"],"knowledge_cutoff":null,"release_date":null,"deprecation_date":null,"retirement_date":null,"aliases":[],"homepage":null,"docs":null,"categories":["ai-ml"],"tags":[],"last_verified":"2026-06-09T00:00:00.000Z","next_check":"2026-09-07T00:00:00.000Z","created_at":"2026-06-09T18:23:25.659Z","updated_at":"2026-06-09T18:23:25.659Z"}