66trust / 100

Embeddings

by Aayat AI in AI models & inference

x402 APIFailing, checked 36 min ago

Text embeddings for semantic search, clustering and RAG: 1024-dimension multilingual vectors (BGE-M3, 100+ languages). POST JSON {"input": ["first text", "second text"]} (up to 32 texts of 8,000 characters) or {"text": "one text"}. One price per call, however many texts. No API key needed.

POST https://aayatai.com/embeddings

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
50.0%
Response time
73 ms typical, 73 ms slowest 5%
Last check
36 min ago: Expected HTTP 402, got 410
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://aayatai.com/embeddings" \
  -H "content-type: application/json" \
  -d '{"input":["x402 lets AI agents pay per API call.","Stablecoin micropayments over HTTP."]}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Faayatai.com%2Fembeddings
const res = await pay("https://aayatai.com/embeddings", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"input":["x402 lets AI agents pay per API call.","Stablecoin micropayments over HTTP."]}),
});
console.log(await res.json());

Example input

{
  "input": [
    "x402 lets AI agents pay per API call.",
    "Stablecoin micropayments over HTTP."
  ]
}

Example output

{
  "dimensions": 1024,
  "embeddings": [
    [
      0.012,
      -0.034,
      0.056
    ],
    [
      0.021,
      -0.011,
      0.047
    ]
  ],
  "model": "@cf/baai/bge-m3"
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
36 min agoExpected HTTP 402, got 41041052 ms-
6 h agoPassed40273 ms$0.002