Skip to content
Eden Engine
Get started

Image Text Extraction (OCR, by URL or Base64)

omnial/x402-image-to-text

Given an image URL or a base64-encoded image, runs OCR and returns the text found in it, a confidence level, the detected language, and a classification of the image, e.g. 'screenshot' (the endpoint also documents 'photo' and 'handwritten note' as possible classifications, though only 'screenshot' has been observed in testing). On an image with no text, returns an empty text string with a null detected language and a null image-type classification.

activeper callv4

Price

Up to $0.0811 per call; you pay what the call used

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.00.

Data source

Anthropic

Text read from the image you provide by Anthropic's Claude.

Use it

Your AI assistant does the work: it finds this tool, shows you the price first, runs it, and you are charged when the run finishes. There is nothing to set up for this tool in particular.

Connect once and your AI can find and run this tool, and any other it needs.

Install itCreate an account
For developers: the calls your assistant makes
agent
// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "omnial/x402-image-to-text" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "omnial/x402-image-to-text" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "omnial/x402-image-to-text", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "omnial/x402-image-to-text", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

ChargePrice
Per call
$0.0811
Updated
Oct 27, 2026

Input and output schemas

Input schema
input_schema.json
{
  "type": "object",
  "anyOf": [
    {
      "required": [
        "image_url"
      ]
    },
    {
      "required": [
        "base64"
      ]
    }
  ],
  "properties": {
    "base64": {
      "type": "string",
      "description": "Base64-encoded image"
    },
    "image_url": {
      "type": "string",
      "description": "URL to image"
    }
  },
  "additionalProperties": false
}
Output schema
output_schema.json
{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The text found in the image. Empty string on the one real no-text case observed (a blank image), not omitted or null."
    },
    "text_type": {
      "type": [
        "string",
        "null"
      ],
      "description": "A classification of the image's content, e.g. 'screenshot'. Observed null on the one real call with no text found; 'screenshot' is the only non-null value observed -- other classifications the endpoint documents (e.g. 'photo', 'handwritten note') were never observed and their shape is unconfirmed."
    },
    "confidence": {
      "type": "string",
      "description": "Confidence level for the extraction. Typically 'high', even for a blank no-text image -- other values (e.g. 'medium'/'low') were never observed and their shape is unconfirmed."
    },
    "language_detected": {
      "type": [
        "string",
        "null"
      ],
      "description": "Detected language of the extracted text, e.g. 'English'. Observed null on the one real call with no text to detect a language from."
    }
  },
  "description": "The OCR result.",
  "additionalProperties": true
}