Image description API: caption, OCR-style reading and visual Q&A
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.
When to use it
- Write alt text for an image at a public URL
- Read the text in screenshots and charts
- Ask a specific question about the image
Guide: Describe image API
Inputs
| Name | Type | Description |
|---|---|---|
url (required) | string | Absolute http(s) URL of a PNG, JPEG, WebP or GIF image (max 3 MB) |
question | string | Optional question about the image (max 300 characters); default is a detailed description |
Request
Over HTTP, with a card key from /credits:
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"
Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum or Solana over x402; Base or Tempo over MPP) and retries.
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"
}
From an AI agent (MCP)
Add the MCP server to Claude, Cursor or any MCP client. This tool is describe, and the first 25 successful calls are free:
https://tools.funwords.eu/mcp
Questions
Which formats and sizes?
PNG, JPEG, WebP and GIF up to 3 MB, by public URL.
Which model answers?
A vision model on Workers AI; its exact name is returned in the model field.
How do I pay?
Each successful call costs $0.01; failed calls are not charged. This tool is not in the free calls; pay with card credits (from $1; the key goes in an Authorization header or, for clients that can only fetch a URL, as api_key= in the URL) or per call in USDC over x402 or MPP. No account is needed.