# GEDX402 Small Text Embedding

> GEDX402 Small Text Embedding is a paid API for AI agents from embed.gedx402.com, paid per call via x402, $0.0036/call, status unknown (last checked 2026-09-15).

Converts text strings into vector embeddings using Workers AI, paid per-call with USDC via x402 — no API key required

## Facts

- Endpoint: GET https://embed.gedx402.com/v1/embed/small
- Price: $0.0036/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-small-text-embedding-6c7942b2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_D9iuJJBaSDUCrLevfpLAr

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 gedx402-small-text-embedding-6c7942b2
```

Example prompt: Embed this sentence into a vector using the GEDX402 small embedding model — no API key, just pay with USDC: 'The quick brown fox jumps over the lazy dog.'

## When to prefer this

Choose this endpoint when you need lightweight text embeddings on a pay-per-call basis without API key management. Ideal for agents that operate with crypto wallets (Base, Polygon, Arbitrum, World, Solana) and need semantic embeddings for RAG, similarity search, or clustering without committing to a subscription. The small model keeps costs low at $0.0036 per call.

## Known failure modes

- Payment not received or insufficient USDC — returns HTTP 402 with payment required details
- Invalid or missing 'text'/'texts' fields — returns 400 bad request
- Text too long for the small model context window — may return 400 or truncated result
- Network timeout on Workers AI backend — returns 5xx error
- Unsupported chain or wallet for USDC payment — payment step fails before API call

## How this service works

Generate text embeddings with BGE Small EN V1.5 (@cf/baai/bge-small-en-v1.5). POST text or texts[] for semantic search, RAG retrieval, and clustering; billed by input character volume.

## Output

A JSON object containing a 'data' array where each element has an 'index' (integer position) and an 'embedding' (array of floats representing the vector). Supports single or batch inputs in one response.

## Request schema (JSON Schema)

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

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-small-text-embedding-6c7942b2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from embed.gedx402.com](https://www.zero.xyz/host/embed.gedx402.com/llms.txt)