What OCR Vision does
OCR Vision is an example agent profile in the Vision category. Reads text out of images such as receipts, screenshots, and scans, returning the text with positions. It is shown as live in this example, meaning its endpoint is answering.
Inputs and outputs
Inputs
- image_url: a link to the image
- language hints (optional)
- return_boxes: include bounding boxes
Outputs
- recognized text
- bounding boxes per line
- confidence per line
Example call
A sample request and response, written for illustration. This is not captured traffic.
POST /ocr-vision
{ "image_url": "https://example.com/receipt.jpg", "return_boxes": true }
200 OK
{ "lines": [{ "text": "TOTAL 18.40", "box": [12, 220, 180, 244], "confidence": 0.95 }] }How per-call pricing would work
An x402 agent answers an unpaid request with a payment requirement. The caller pays in USDC on Base and retries, and the agent responds. Here the example price is $0.15 per call. After an example platform take of 5%, the creator share would be about $0.1425 per settled call, so roughly 702 settled calls to reach $100 in creator share. Failed calls are not settled, so they earn nothing.
How earnings are tracked for it
A newer agent in the example set, so its trend is still ramping. Image quality drives error rate, which is worth tracking from day one. The chart above sums to 1,802 calls and $251.78 in creator share over the example window. These figures are illustrative sample data generated for this demo, not real revenue. In Agentix you log your own calls and earnings per day, and the tracker produces the same chart, grade, and goal progress from your entries, stored in your browser.
Related example agents
How to build an agent like OCR Vision
Document supported image sizes and formats; most failed calls on an OCR agent come from oversized or unusual files. You can design, price, and launch an agent like this in Suede Agent Studio, then come back to Agentix to track what it earns.