# Agent Data Tools: Text Embedding

> Agent Data Tools: Text Embedding is a paid API for AI agents from agent-data-tools.revmesh2074.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-28).

Converts input text (up to 4,000 characters) into a 1024-dimensional numerical embedding vector using the BAAI BGE-M3 model

## Facts

- Endpoint: GET https://agent-data-tools.revmesh2074.workers.dev/ai/embed?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-tools-text-embedding-47010af0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bQyQJmxnn1zxceWYLIw7r

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 agent-data-tools-text-embedding-47010af0
```

Example prompt: Embed this text for me using BGE-M3: 'Retrieval-augmented generation combines large language models with external knowledge sources to produce more accurate and grounded responses.' I need the 1024-dimensional vector so I can store it in my vector database.

## When to prefer this

Choose this endpoint when you need a pay-per-call, no-account embedding service using the multilingual BGE-M3 model at $0.002 per call with x402 USDC micropayments on Base. Ideal for AI agents that need on-demand embeddings without managing API keys or subscriptions, and that already use the Agent Data Tools suite for crypto, web, or business data. BGE-M3 provides strong multilingual and cross-lingual retrieval performance at 1024 dimensions.

## Known failure modes

- Text exceeds 4,000 character limit — embedding may be truncated or rejected
- Missing required 'text' query parameter returns an error
- Payment failure in x402 protocol results in no charge and no response
- Model inference timeout on very dense or unusual text
- Network errors to Cloudflare Workers endpoint

## How this service works

A 1,024-dimension embedding vector for up to 4,000 characters of text in 100+ languages, from BAAI's BGE-M3. Use for semantic search, RAG retrieval, clustering and deduplication.

## Output

Returns a JSON object containing the model name ('model': '@cf/baai/bge-m3'), a 1024-dimensional floating-point array ('embedding': [float, ...]) representing the semantic content of the input text, and a dimension count ('dimensions': 1024). The embedding can be used directly for cosine similarity, nearest-neighbor search, or storage in a vector database.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to embed, up to 4,000 characters"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string"
  },
  "embedding": {
   "type": "array",
   "items": {
    "type": "number"
   }
  },
  "dimensions": {
   "type": "number"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-tools-text-embedding-47010af0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data-tools.revmesh2074.workers.dev](https://www.zero.xyz/host/agent-data-tools.revmesh2074.workers.dev/llms.txt)