EmbedPay

What it does

POST text and receive a vector embedding from OpenAI text-embedding-3-small (1536 dimensions). No account, no API key, no subscription — pay per 1k tokens via x402. Single input or batch (array). Batch of ≥100 inputs gets reduced pricing ($0.00003/1k tokens vs $0.00005/1k standard). Token counting uses cl100k_base (same as OpenAI) for honest billing — you can verify the token count yourself. Input tokens and model version are always returned so you know exactly what you paid for. Models: openai-3-small (default, 1536d), openai-3-large (3072d). Composes naturally with ScrapePay → MarkdownOpt → EmbedPay → vector DB.

When to use it

• RAG pipeline: ScrapePay → MarkdownOpt → EmbedPay → insert into Qdrant/Pinecone
• Semantic search over agent memory: embed each memory chunk for cosine similarity retrieval
• Batch-embed a corpus of documents at batch pricing before ingestion
• Duplicate detection: embed two texts and compare cosine similarity

Request schema

{
  "input": "The quick brown fox jumps over the lazy dog",
  "model": "openai-3-small"
}

Response schema

{
  "success": true,
  "embedding": [
    0.0123,
    -0.0456,
    0.0789
  ],
  "model": "openai-3-small",
  "dimensions": 1536,
  "input_tokens": 9,
  "model_version": "text-embedding-3-small (2024-01-25)",
  "payment_hash": "0x..."
}

Code example — TypeScript via MCP

Install the MCP server once; all 22 services become tool calls.

// Configure @melis-ai/x402-tools-mcp in your MCP client
// Then call the tool:

const result = await mcpClient.callTool("embedpay", {
  "input": "The quick brown fox jumps over the lazy dog",
  "model": "openai-3-small"
});

console.log(result);
// ["success","embedding","model","dimensions","input_tokens","...

Code example — Python via direct HTTP

import requests

# x402 payment header must be set by your wallet client
# See x402.org for client libraries

headers = {
    "Content-Type": "application/json",
    "x-payment": "<signed-x402-payment-header>",
}

resp = requests.post(
    "https://embedpay.melis.ai/embed",
    json={
      "input": "The quick brown fox jumps over the lazy dog",
      "model": "openai-3-small"
    },
    headers=headers,
)
print(resp.json())

Code example — curl with internal key bypass

For testing with an issued internal key (skips x402 payment flow):

curl -X POST https://embedpay.melis.ai/embed \
  -H "Content-Type: application/json" \
  -H "x-internal-key: YOUR_KEY" \
  -d '{"input":"The quick brown fox jumps over the lazy dog","model":"openai-3-small"}'

How is this different from alternatives?

Related services

FAQ