agentutility$ man describe-image
/describe-image
NAME
describe-image — ai image descriptor / vision llm
SYNOPSIS
POST https://x402.agentutility.ai/describe-image
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
AI image descriptor / vision LLM. Modes: describe, alt_text (accessibility, ≤125 chars), OCR (extract visible text), tags (8-15 keywords), caption (single-sentence). Vision LLM powered.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| image_url | string | Public URL of an image. | required |
| mode | string | 'describe' (default), 'alt_text', 'ocr', 'tags', 'caption'. enum: describe · alt_text · ocr · tags · caption | optional |
| prompt | string | Optional custom instruction. Overrides mode. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| text | string | Generated output for the selected mode: prose description, alt text, extracted OCR text, keyword list, or caption. |
| mode | string | Mode used to generate the output: describe, alt_text, ocr, tags, or caption. |
| image_url | string | URL of the source image that was analyzed by the vision LLM. |
| model | string | Vision LLM model name that produced the description (e.g. claude-haiku-4-5). |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/describe-image \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# MCP packages on npm under # @agentutility/mcp-* (one per cluster) # # Catalog + install: # https://mcp.agentutility.ai # # Or call describe-image directly over HTTP — see above.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- imagevisionocralt-textcaptionaillm
- env
- VENICE_API_KEY
- methods
- POST
- cluster
- wordmint
- price
- $0.02 USDC per call
ADJACENT — other endpoints in wordmint
| endpoint | description | price |
|---|---|---|
| classify | Zero-shot text classifier. | $0.02 |
| classify-text | Text classifier / zero-shot classifier / category sorter. | $0.02 |
| detect-pii | PII detector / data leak scanner. | $0.02 |
| email-draft | AI email writer / cold outreach / follow-up generator. | $0.02 |
| extract | Named entity extractor / NER. | $0.02 |
| moderate-content | Content moderation / safety classifier / OpenAI-style toxicity API. | $0.02 |
| resume-scorer | AI resume scorer / ATS keyword analyzer. | $0.02 |
| rewrite-tone | Tone rewriter / paraphraser / writing style changer. | $0.02 |
SEE ALSO