Drop-in OpenAI Embeddings endpoint: POST {input: string | string[], model, encoding_for…

What it does

Drop-in OpenAI Embeddings endpoint: POST {input: string | string[], model, encoding_format: float|base64, dimensions} and get {object: "list", data: [{embedding, index}], model, usage}. Models (Cloudflare Workers AI): bge-m3 (1024-d, multilingual (100+ languages), 8192-token context); bge-large-en-v1.5 (1024-d, English); bge-base-en-v1.5 (768-d, English); bge-small-en-v1.5 (384-d, English, fastest); embeddinggemma-300m (768-d, multilingual (Google EmbeddingGemma)). Any other model name (e.g. text-embedding-3-small) maps to bge-m3; the actual model is in the response. `dimensions` truncates and re-normalizes. Up to 100 inputs per call, 8000 chars each, 60000 chars total, one fixed price per call. For RAG, semantic search, clustering and dedupe. Errors are never charged. GET ?input= also works; with no params it embeds a sample sentence.

Tags: embeddings · openai-compatible · rag · vector · ai

Call contract

Method

HTTP

Input

HTTP request

Output

json

Use with an agent

1. Discover. Agents find this listing with GET https://bazaar.saylorinnovations.com/discovery/search?query=…, the MCP tool search_resources, or /discovery/resources.
2. Inspect. Fetch /resources/69288.json for the price and payment options.
3. Pay. Call GET https://quickbuild.quynguyenbac.workers.dev/v1/embeddings. The provider answers 402 with its payment requirements. An x402 client signs one of the options below and retries with PAYMENT-SIGNATURE.
4. Execute. The provider returns 200 with the data. Agent Bazaar is not in the request path and never sees your payment.

For humans

You don't need an account or an API key; you need a wallet holding a small amount of USDC on Base, and an x402-capable client (see the examples below). Call the endpoint unpaid first to see exactly what it asks for.

Pricing & payment

Price

$0.001 / request

Protocol

x402 v2

Auth

No account or API key. Pay per request.

Networks

Base

x402 payment requirements

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0x751a4c3841bE287544C371B4EE09Bd3366AeA7cf",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "1000",
    "amountUsd": 0.001,
    "maxTimeoutSeconds": 300
  }
]

Examples

curl -X GET 'https://quickbuild.quynguyenbac.workers.dev/v1/embeddings'
# -> 402 Payment Required; read PAYMENT-REQUIRED
# retry the identical request with PAYMENT-SIGNATURE

const res = await fetch("https://quickbuild.quynguyenbac.workers.dev/v1/embeddings", {
  "method": "GET"
});
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}

import httpx
res = httpx.request("GET", "https://quickbuild.quynguyenbac.workers.dev/v1/embeddings")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header

Details

Provider

QuickBuild agent APIs (incl. LaunchCheck)

Endpoint

https://quickbuild.quynguyenbac.workers.dev/v1/embeddings

Machine-readable

/resources/69288.json