81trust / 100

Embeddings

by Embeddings (OpenAI-compatible) in AI models & inference

x402 APIPassing, checked 1 h ago

OpenAI-compatible text embeddings (text-embedding-3-small by default; 3-large and ada-002 supported), up to 64 inputs or 16k chars per call, returned in the standard OpenAI shape. Identical inputs repeated within 10 minutes are served free from cache. Use it for semantic search, clustering and retrieval from any OpenAI SDK by changing base_url.

POST https://agent402.tools/v1/embeddings

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
218 ms typical, 329 ms slowest 5%
Last check
1 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://agent402.tools/v1/embeddings" \
  -H "content-type: application/json" \
  -d '{"input":"Agent402 is an open-source x402 tool server."}'
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%2Fagent402.tools%2Fv1%2Fembeddings
const res = await pay("https://agent402.tools/v1/embeddings", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"input":"Agent402 is an open-source x402 tool server."}),
});
console.log(await res.json());

Example input

{
  "input": "Agent402 is an open-source x402 tool server."
}

Example output

{
  "data": [
    {
      "embedding": [
        0.0023,
        -0.0091,
        0.0152
      ],
      "index": 0,
      "object": "embedding"
    }
  ],
  "model": "text-embedding-3-small",
  "object": "list",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
1 h agoPassed402199 ms$0.002
5 h agoPassed402487 ms$0.002
9 h agoPassed402218 ms$0.002
12 h agoPassed402191 ms$0.002
16 h agoPassed402184 ms$0.002
19 h agoPassed402307 ms$0.002
23 h agoPassed402329 ms$0.002
28 h agoPassed402314 ms$0.002