# Describe image API

Give an image URL and get a detailed description including any visible text, or ask a question about the image; PNG, JPEG, WebP and GIF up to 3 MB.

## When an agent wants this

- Write alt text
- Read the text in a screenshot or chart
- Check what a picture shows before an agent uses it

## Describe image, ask about it: ask what is in an image or photo at a URL and get a text description or answer

Describe image, ask about it: ask what is in an image or photo at a URL and get a text description or answer. $0.01 per successful call; failed calls are never charged.

Vision model for an image at a public URL: get a detailed description including any visible text, or pass a question to ask something specific about the image. Accepts PNG, JPEG, WebP and GIF up to 3 MB. Use for alt text, OCR-style reading of screenshots, chart reading and content checks.

Inputs: url (required): Absolute http(s) URL of a PNG, JPEG, WebP or GIF image (max 3 MB); question: Optional question about the image (max 300 characters); default is a detailed description.

Not in the free calls (it costs us capacity per call); pay from the first call.

With a card key from https://tools.funwords.eu/credits, in a header or, when your client can only fetch a URL, in the URL:

    curl -H "Authorization: Bearer adt_…" "https://tools.funwords.eu/describe?url=https%3A%2F%2Fupload.wikimedia.org%2Fwikipedia%2Fcommons%2F4%2F47%2FPNG_transparency_demonstration_1.png"
    curl "https://tools.funwords.eu/describe?url=https%3A%2F%2Fupload.wikimedia.org%2Fwikipedia%2Fcommons%2F4%2F47%2FPNG_transparency_demonstration_1.png&api_key=adt_…"

Without a key the same URL answers 402 with x402 and MPP terms, so a wallet client pays USDC per call and retries. Over MCP (https://tools.funwords.eu/mcp) this tool is describe.

Example result:

    {
      "url": "https://upload.wikimedia.org/wikipedia/commons/4/47/PNG_transparency_demonstration_1.png",
      "question": "What colors are the dice?",
      "description": "The dice are blue, red, green, and yellow.",
      "model": "@cf/meta/llama-4-scout-17b-16e-instruct"
    }

Tool page: https://tools.funwords.eu/tools/describe

## Questions

**Which model answers?** A vision model on Workers AI; its name is returned in the model field.

Docs for agents: https://tools.funwords.eu/llms.txt · OpenAPI: https://tools.funwords.eu/openapi.json · All guides: https://tools.funwords.eu/guides