{"slug":"vision","domain":"documents","title":"A question answered about an image","summary":"A vision model reads images from a drive or a url and answers in words: what is in it, what it says, whether two match.","help":"vision: ask about an image, as JSON.\n\nTAKES URLS\n  Comma-separate several for `ask`. Not local files.\n\nStudies:\n  ask \u003cprompt\u003e \u003cimages\u003e\n      ask a question about one or more images, on a drive or at a url — comma-separate them\n\nJSON to stdout, so it composes: pipe to `jq` to pick a field, or `\u003e /tmp/…` to keep it.\nRun a study with no arguments — `vision ask` — to see what it takes.\n","example_command":"vision ask \"which of these is a serial number plate?\" https://example.com/a.jpg,https://example.com/b.jpg","example_output":"","cost_class":"upstream-fetch","tier":"metered","billing_items":["gemini-2.5-flash"],"price_per_1k_calls":null,"price_is_from":true,"status":"available","commands":["vision"],"studies":[{"call":"ask","about":"ask a question about one or more images, on a drive or at a url — comma-separate them","args":[{"name":"prompt","positional":true,"list":false,"hint":""},{"name":"images","positional":true,"list":true,"hint":""}]}],"default_enabled":false,"first_seen":"2026-09-09T04:30:35.160951Z","enabled":false}