{"slug":"google/vit-base-patch16-224","title":"ViT Base Patch16 224","description":"A Vision Transformer (ViT) base model pre-trained on ImageNet-21k and fine-tuned on ImageNet-1k at 224x224 resolution.","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":"https://huggingface.co/google/vit-base-patch16-224","docs":null,"categories":["ai-ml"],"tags":[],"last_verified":"2026-06-09T00:00:00.000Z","next_check":"2026-09-07T00:00:00.000Z","created_at":"2026-06-09T18:21:39.274Z","updated_at":"2026-06-09T18:21:39.274Z"}