81trust / 100

Embeddings

by NetIntel in AI models & inference

x402 APIPassing, checked 4 h ago

Multilingual text embeddings (384-dim) served in-house, no OpenAI dependency, no API key. NetIntel's cheapest embeddings at $0.001/call, batches up to 256 texts. Supports query/passage input types for retrieval (e5). Pairs with /text/chunk for a full chunk→embed RAG pipeline on one provider.

POST https://netintel.dev/embeddings

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
183 ms typical, 183 ms slowest 5%
Last check
4 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://netintel.dev/embeddings" \
  -H "content-type: application/json" \
  -d '{"input":"the quick brown fox","input_type":"passage"}'
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%2Fnetintel.dev%2Fembeddings
const res = await pay("https://netintel.dev/embeddings", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"input":"the quick brown fox","input_type":"passage"}),
});
console.log(await res.json());

Example input

{
  "input": "the quick brown fox",
  "input_type": "passage"
}

Example output

{
  "data": [
    {
      "embedding": [
        0.0123,
        -0.0456,
        0.0789
      ],
      "index": 0,
      "object": "embedding"
    }
  ],
  "dimensions": 384,
  "findings": [],
  "input_type": "passage",
  "model": "netintel-embed-small",
  "normalized": true,
  "object": "list",
  "provider": "netintel",
  "source_model": "multilingual-e5-small",
  "usage": {
    "prompt_tokens": 6,
    "total_tokens": 6
  }
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
4 h agoPassed402183 ms$0.001