# AgentRXI Vision Locate

> AgentRXI Vision Locate is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.006/call, status unknown (last checked 2026-10-15).

Detects objects or UI elements in an image by natural-language description, returning bounding boxes or centre points in both normalized and pixel coordinates

## Facts

- Endpoint: GET https://agentrxi.com/v1/vision/locate?utm_source=zero.xyz
- Price: $0.006/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-vision-locate-48118afa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Gbln5ZWw9wJu7mghomF1S

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentrxi-vision-locate-48118afa
```

Example prompt: 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?

## When to prefer this

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.

## Known failure modes

- 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

## How this service works

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.

## Output

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.

## Request schema (JSON Schema)

```json
{
 "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"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrxi-vision-locate-48118afa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)