# GED x402 Gemma-300M Text Embedding

> GED x402 Gemma-300M Text Embedding is a paid API for AI agents from ged-x402-embed.jvalamis.workers.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-15).

Generates vector embeddings for text using a Gemma-300M model, payable with USDC via x402 protocol — no API keys required.

## Facts

- Endpoint: GET https://ged-x402-embed.jvalamis.workers.dev/v1/embed/embeddinggemma-300m
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ged-x402-gemma-300m-text-embedding-e3c13cc1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_k8jfuYhZTMCLbT1UGBXBf

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 ged-x402-gemma-300m-text-embedding-e3c13cc1
```

Example prompt: Can you embed this text into a vector using the Gemma-300M model: 'The quick brown fox jumps over the lazy dog'? Pay with USDC — no API key needed.

## When to prefer this

Choose this endpoint when you need text embeddings without setting up API keys or managing credentials — ideal for autonomous agents that can pay per-call in USDC on Base, Polygon, Arbitrum, World, or Solana. It is well-suited for RAG pipelines, semantic search indexing, or similarity tasks where the Gemma-300M model's quality is sufficient and cost-per-call simplicity matters.

## Known failure modes

- Payment not completed or USDC balance insufficient — HTTP 402 returned
- Invalid or missing 'text' and 'texts' fields — malformed request
- Model inference timeout on Cloudflare Workers edge
- Empty input string causes degenerate or error embedding
- Unsupported blockchain network for payment fails the x402 handshake

## How this service works

x402 workers ai. pay with usdc on base, polygon, arbitrum, world, or solana. no api keys.

## Output

A JSON object with a 'data' array, each element containing an 'index' and an 'embedding' field — the embedding is a float array representing the semantic vector of the input text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string"
  },
  "texts": {
   "type": "array",
   "items": {
    "type": "string"
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": [
   {
    "index": 0,
    "embedding": [
     0.01,
     -0.02
    ]
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ged-x402-gemma-300m-text-embedding-e3c13cc1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ged-x402-embed.jvalamis.workers.dev](https://www.zero.xyz/host/ged-x402-embed.jvalamis.workers.dev/llms.txt)