# Forgemesh Picture Summary API

> Forgemesh Picture Summary API is a paid API for AI agents from x402.forgemesh.io, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).

Describes the contents of any publicly hosted image in plain sentences, including what's in it, the setting, what's happening, and any visible text.

## Facts

- Endpoint: POST https://x402.forgemesh.io/picture-summary
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-picture-summary-api-15079c31
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5OdnF1MIS0V4loQXihdnU

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 forgemesh-picture-summary-api-15079c31 -d '<json body>'
```

Example prompt: Can you describe what's in this image for me? Here's the URL: https://example.com/photos/event-photo.jpg — tell me what's in it, where it's set, what's happening, and any text visible in the frame.

## When to prefer this

Use this endpoint when you need a stateless, pay-per-call image description without storing any data — ideal for content moderation pipelines, auto-tagging media libraries, or giving a non-visual AI agent the ability to reason about an image via its URL. Prefer this over general vision APIs when privacy (no retention) and cost predictability ($0.01/call) matter.

## Known failure modes

- Image URL is not publicly accessible (returns error)
- Image exceeds 8MB size limit (rejected)
- Unsupported image format beyond jpg/png/webp (rejected)
- Image URL returns a non-image content type (error)
- Network timeout fetching the remote image

## How this service works

Picture summary API: describes the contents of any publicly hosted image in plain sentences, what's in it, where it's set, what's happening, and any text visible in the frame. Nothing is saved after the request completes. For content moderation queues, media library tagging, and giving non-visual agents a way to reason about images.

## Output

A plain-English paragraph or set of sentences describing the image contents: subjects, scene/setting, actions occurring, and any text visible in the image frame. No data is retained after the request.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "image_url": {
   "type": "string",
   "description": "Public URL of the image (jpg/png/webp, max 8MB)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "A teal rectangular graphic with the words FORGEMESH UTILITY GRID in bold white capital letters centered on it.",
  "model": "moondream"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/forgemesh-picture-summary-api-15079c31/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.forgemesh.io](https://www.zero.xyz/host/x402.forgemesh.io/llms.txt)