Embeddings

Converts text into numeric vectors for semantic search, clustering, and RAG. Compatible with OpenAI’s POST /v1/embeddings.

POST https://api.norlen.io/v1/embeddings
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Parameters

Field	Type	Required	Description
`model`	string	yes	`qwen3-embedding`
`input`	string \| array	yes	A single text or a list of texts to vectorize
`encoding_format`	string	no	`float` (default) or `base64`

Example

curl https://api.norlen.io/v1/embeddings \
  -H "Authorization: Bearer $NORLEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-embedding",
    "input": "Intelligence infrastructure for people who build products."
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.norlen.io/v1", api_key="your-token")

resp = client.embeddings.create(
    model="qwen3-embedding",
    input=["first text", "second text"],
)
print(len(resp.data), "vectors")
print(resp.data[0].embedding[:5])

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.norlen.io/v1",
  apiKey: process.env.NORLEN_API_KEY,
});

const resp = await client.embeddings.create({
  model: "qwen3-embedding",
  input: ["first text", "second text"],
});
console.log(resp.data[0].embedding.slice(0, 5));

Response

{
  "object": "list",
  "model": "qwen3-embedding",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0123, -0.0456, 0.0789, "..."] }
  ],
  "usage": { "prompt_tokens": 12, "total_tokens": 12 }
}