# CryptoRisk API - Text Embeddings (jina-embeddings-v3)

> CryptoRisk API - Text Embeddings (jina-embeddings-v3) is a paid API for AI agents from cryptorisk-api.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Converts text into dense vector embeddings using jina-embeddings-v3, supporting batch processing of up to 64 texts per call.

## Facts

- Endpoint: POST https://cryptorisk-api.vercel.app/api/embed
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cryptorisk-api-text-embeddings-jina-embeddings-v3-328cde9f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UKYSPwzymNtxKAVi7rvMZ

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 cryptorisk-api-text-embeddings-jina-embeddings-v3-328cde9f -d '<json body>'
```

Example prompt: Convert these 3 product descriptions into vector embeddings using jina-embeddings-v3 so I can index them for semantic search: 'Wireless noise-cancelling headphones', 'Bluetooth portable speaker', 'USB-C wired earbuds'.

## When to prefer this

Choose this endpoint when you need pay-per-call text embeddings using jina-embeddings-v3 with no API key or account registration required, especially for low-volume or sporadic workloads where a subscription is not cost-effective. Ideal for agents operating in x402 micropayment environments that need to embed batches of up to 64 texts on demand.

## Known failure modes

- Batch size exceeds 64 texts — request rejected
- Empty or missing text input — validation error
- Payment not attached or insufficient USDC — 402 Payment Required
- Text too long for model context window — truncation or error
- Vercel cold start causing occasional latency spike

## How this service works

Embeddings: text -> vectors (jina-embeddings-v3). Batch up to 64.

## Output

An array of dense float vectors (one per input text), each corresponding to a jina-embeddings-v3 embedding of the submitted text. Vectors can be used directly for similarity search, clustering, classification, or indexing into a vector database.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cryptorisk-api-text-embeddings-jina-embeddings-v3-328cde9f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cryptorisk-api.vercel.app](https://www.zero.xyz/host/cryptorisk-api.vercel.app/llms.txt)