# JigsawStack Multimodal Vector Embedding

> JigsawStack Multimodal Vector Embedding is a paid API for AI agents from jigsawstack.withzero.ai, paid per call via MPP, $0.001/call, status unknown (last checked 2026-09-15).

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

## Facts

- Endpoint: POST https://jigsawstack.withzero.ai/v1/embedding
- Price: $0.001/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Provider: jigsawstack.withzero.ai
- Website: https://jigsawstack.withzero.ai
- Canonical page: https://www.zero.xyz/c/jigsawstack-withzero-ai-embedding-9245e85f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cBG879FN5H9qF5RtMRkod

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 jigsawstack-withzero-ai-embedding-9245e85f -d '<json body>'
```

Example prompt: Generate a vector embedding for this text using JigsawStack's multimodal embedding API: 'The quick brown fox jumps over the lazy dog' — I need the float array to store in my vector database for semantic search.

## When to prefer this

Choose this endpoint when you need multimodal embedding support in a single API — especially when your pipeline needs to embed text, images, audio, and PDFs using a consistent vector space. Prefer this over text-only embedding APIs when your data is mixed-modality. Ideal for RAG pipelines, semantic search indexes, and similarity matching tasks that span content types.

## Known failure modes

- Unsupported input type — only text, image URL, audio, and PDF are accepted
- Input too large — exceeds size limits for the given modality
- Invalid or inaccessible URL for image/audio/PDF inputs
- Malformed request body — missing required input field
- Payment failure — insufficient USDC balance for the $0.001 per-call fee

## How this service works

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

## Output

Returns a JSON object containing the vector embedding as a float array representing the semantic meaning of the input, usable for similarity search, clustering, or storage in a vector database.

## Example request

```json
{
 "text": "Artificial intelligence and machine learning are transforming modern technology."
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "The text to generate a vector embedding for."
  }
 },
 "additionalProperties": false
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "success",
  "embeddings",
  "chunks",
  "_usage",
  "log_id"
 ],
 "properties": {
  "_usage": {
   "type": "object",
   "required": [
    "input_tokens",
    "output_tokens",
    "inference_time_tokens",
    "total_tokens"
   ],
   "properties": {
    "input_tokens": {
     "type": "number"
    },
    "total_tokens": {
     "type": "number"
    },
    "output_tokens": {
     "type": "number"
    },
    "inference_time_tokens": {
     "type": "number"
    }
   }
  },
  "chunks": {
   "type": "array",
   "items": {
    "type": "string"
   }
  },
  "log_id": {
   "type": "string"
  },
  "success": {
   "type": "boolean"
  },
  "embeddings": {
   "type": "array",
   "items": {
    "type": "array",
    "items": {
     "type": "number"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/jigsawstack-withzero-ai-embedding-9245e85f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from jigsawstack.withzero.ai](https://www.zero.xyz/host/jigsawstack.withzero.ai/llms.txt)