{"slug":"depth-anything/prompt-depth-anything-vitl-hf","title":"Prompt Depth Anything ViT-L","description":"A promptable depth estimation model using a Vision Transformer large backbone, enabling conditional depth prediction from user prompts.","provider":"depth-anything","model_type":"vision","status":"active","context_window":null,"max_output_tokens":null,"pricing":null,"modalities":["image"],"capabilities":["vision"],"knowledge_cutoff":null,"release_date":"2024-11-01T00:00:00.000Z","deprecation_date":null,"retirement_date":null,"aliases":[],"homepage":"https://huggingface.co/depth-anything/prompt-depth-anything-vitl-hf","docs":null,"categories":["ai-ml"],"tags":[],"last_verified":"2026-06-09T00:00:00.000Z","next_check":"2026-09-07T00:00:00.000Z","created_at":"2026-06-09T18:30:37.676Z","updated_at":"2026-06-09T18:30:37.676Z"}