# JarvisClaw Embeddings API

> JarvisClaw Embeddings API is a paid API for AI agents from uat.jarvisclaw.ai, paid per call via x402, $0.045/call, status unknown (last checked 2026-09-15).

Converts text into vector embeddings using an OpenAI-compatible API gateway, paid per call via x402 in USDC on Base or Solana.

## Facts

- Endpoint: POST https://uat.jarvisclaw.ai/v1/embeddings
- Price: $0.045/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/jarvisclaw-embeddings-api-647c603b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wOhxl2TvQLcnbUOon-5ou

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 jarvisclaw-embeddings-api-647c603b -d '<json body>'
```

Example prompt: Embed the text 'The quick brown fox jumps over the lazy dog' using the text-embedding-3-small model through JarvisClaw so I can store it in my vector database.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible text embeddings with pay-per-call crypto billing (USDC on Base or Solana via x402), avoiding subscription commitments. Ideal for agents operating in Web3-native stacks or when you want decentralized, metered AI infrastructure. Not recommended for production workloads given the UAT subdomain.

## Known failure modes

- Payment failure if insufficient USDC balance — returns 402 Payment Required
- Invalid or unsupported model name — returns 400 Bad Request
- Empty or missing input text — returns 400 Bad Request
- Rate limiting if request volume exceeds gateway limits — returns 429 Too Many Requests
- Service unavailability on UAT environment — returns 503 Service Unavailable

## How this service works

AI API Gateway with smart routing, pay per call via x402. OpenAI-compatible. Settled in USDC on Base & Solana.

## Output

Returns an OpenAI-compatible JSON response containing the embedding vector (array of floats) for the input text, along with the model used and token usage statistics.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/jarvisclaw-embeddings-api-647c603b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from uat.jarvisclaw.ai](https://www.zero.xyz/host/uat.jarvisclaw.ai/llms.txt)