# AgentRXI Image Description & OCR

> AgentRXI Image Description & OCR is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.009/call, status unknown (last checked 2026-10-15).

Describes an image and extracts all visible text using a vision LLM, given a public image URL or base64-encoded image with an optional custom question.

## Facts

- Endpoint: GET https://agentrxi.com/v1/image/describe?utm_source=zero.xyz
- Price: $0.009/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-image-description-ocr-d7a9a863
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bM4DHgPLvamm6j-rNtNEF

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-image-description-ocr-d7a9a863
```

Example prompt: Can you describe this image and read all the text in it? Here's the URL: https://example.com/receipt.jpg — I want to know what it shows and every word visible on it.

## When to prefer this

Use this endpoint when you need to both describe an image's visual content AND extract all readable text in a single call. It is ideal for receipts, screenshots, signs, charts, and documents where you need OCR plus scene understanding. Prefer this over a pure OCR service when you also need a description or want to ask a specific question about the image.

## Known failure modes

- Image URL is not publicly accessible or returns a non-200 response
- Image format is unsupported (only jpeg, png, webp, gif are accepted)
- Image exceeds the 8 MB size limit
- Both url and image_base64 are omitted — neither input provided
- Low-quality or blurry images may result in incomplete or inaccurate text extraction
- Payment not included or insufficient USDC balance results in 402 error

## How this service works

Describe an image and read every piece of visible text in it (vision LLM). Send a public image URL or base64 image; optional custom question. Works for receipts, screenshots, signs and charts. Also callable as GET with the same fields as query parameters.

## Output

A natural language description of the image contents plus a full transcription of all visible text. If a custom question/prompt was provided, the response also directly answers that question about the image.

## 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",
     "properties": {
      "url": {
       "type": "string",
       "description": "Public image URL (jpeg, png, webp, gif; max 8 MB)"
      },
      "prompt": {
       "type": "string",
       "description": "Optional question about the image"
      },
      "image_base64": {
       "type": "string",
       "description": "Alternative to url"
      }
     }
    }
   },
   "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-image-description-ocr-d7a9a863/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)