{"uid":"cap_Gbln5ZWw9wJu7mghomF1S","slug":"agentrxi-vision-locate-48118afa","name":"AgentRXI Vision Locate","description":"Find things in an image by description (open-vocabulary detection): bounding boxes (mode=detect) or centre points (mode=point) for any phrase, e.g. 'the Submit button' or 'person in a red jacket', in 0-1 and pixel coordinates. Also callable as GET with the same fields as query parameters.","url":"https://agentrxi.com/v1/vision/locate?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["target"],"properties":{"mode":{"type":"string","description":"detect (boxes, default) or point"},"target":{"type":"string","description":"What to find"},"image_url":{"type":"string"},"max_objects":{"type":"integer"},"image_base64":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.006","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.006/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_eI5YraI8-7icbAMUlQMcU","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.006","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Detects objects or UI elements in an image by natural-language description, returning bounding boxes or centre points in both normalized and pixel coordinates","exampleAgentPrompt":"In this screenshot I just sent you, can you find the 'Sign In' button and tell me its exact position — use detect mode and give me the bounding box coordinates?","exampleUseCases":[{"title":"UI element detection for automation","prompt":"I have a screenshot of a web app — can you locate the 'Add to Cart' button in it and give me its bounding box so my automation script knows where to click?"},{"title":"Person detection in event photo","prompt":"Look at this event photo and find everyone wearing a blue lanyard — I want the bounding boxes for all of them, up to 10 people."},{"title":"Product placement verification","prompt":"Here's an image of our store shelf — can you find where the 'Coca-Cola 500ml bottle' appears and give me the centre point coordinates for each one?"}],"resultDescription":"Returns detected object locations as a list of bounding boxes (mode=detect, default) or centre points (mode=point), each with both normalized 0-1 coordinates and absolute pixel coordinates, matched to the target phrase provided.","failureModes":["Image URL is inaccessible or returns a non-image response — detection fails with an error","Target phrase is too ambiguous or matches nothing in the image — returns empty results","Base64 image data is malformed or too large — request rejected","max_objects exceeded or invalid integer — parameter error returned","Payment not completed via x402 protocol — 402 response before processing begins"],"whenToPreferThis":"Choose this endpoint when you need open-vocabulary, free-text-described object or UI-element detection — i.e., you don't have a fixed class list and want to locate anything describable in natural language. Ideal for UI automation (finding buttons, form fields), visual QA, robotics pipelines, or any agent that needs spatial awareness of image content. Prefer over fixed-class YOLO-style detectors when the target concept is arbitrary or described in prose.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:39:28.122Z","isFirstParty":false,"canonicalSlug":"agentrxi-vision-locate-48118afa"}