# JigsawStack Multimodal Vector Embedding

> JigsawStack Multimodal Vector Embedding is a paid API for AI agents from zero-jigsaw.zclk.cc, price unknown, status down (last checked 2026-10-15).

Generates vector embeddings from text, image, audio, or PDF inputs for semantic search, similarity, and retrieval use cases.

## Facts

- Endpoint: POST https://zero-jigsaw.zclk.cc/v1/embedding?utm_source=zero.xyz
- Price: price unknown
- Status: down
- Last checked: 2026-10-15
- Activations on Zero: 0
- Provider: zero-jigsaw.zclk.cc
- Website: https://zero-jigsaw.zclk.cc
- Canonical page: https://www.zero.xyz/c/zero-jigsaw-zclk-cc-embedding-3b3e72b1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YImYJN1io67r4S_D14g5W

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 zero-jigsaw-zclk-cc-embedding-3b3e72b1 -d '<json body>'
```

Example prompt: Generate a vector embedding for this product description text so I can store it in my vector database and use it for semantic similarity search: 'Lightweight running shoes with breathable mesh upper and responsive foam cushioning, ideal for road running.'

## When to prefer this

Choose this endpoint when you need multimodal vector embeddings across text, image, audio, and PDF in a single unified API, especially in a pay-per-call context settled via USDC. Prefer over OpenAI/Cohere embeddings when you need non-text modalities or want micropayment-based billing without subscription overhead.

## Known failure modes

- Unsupported input modality returns an error
- Image or audio URL is inaccessible or returns non-200 — embedding fails
- PDF exceeds size limits — processing error returned
- Input text is empty or null — validation error
- Network timeout on large audio or PDF files
- Invalid URL format for media inputs

## How this service works

Vector embedding for text/image/audio/pdf inputs (JigsawStack multimodal).

## Output

Returns a JSON object containing the vector embedding as an array of floating-point numbers representing the semantic encoding of the provided input (text, image, audio, or PDF), ready for use in similarity search, clustering, or retrieval systems.

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/zero-jigsaw-zclk-cc-embedding-3b3e72b1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from zero-jigsaw.zclk.cc](https://www.zero.xyz/host/zero-jigsaw.zclk.cc/llms.txt)