Endpoints

Embeddings

Creates dense vector embeddings representing the input text. OpenAI-compatible.

POST /api/v1/embeddings

curl https://api.pendra.ai/api/v1/embeddings \
  -H "Authorization: Bearer pdr_sk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nomic-embed-text",
    "input": [
      "The quick brown fox",
      "jumps over the lazy dog"
    ]
  }'

from pendra import Pendra

client = Pendra()
result = client.embeddings.create(
    model="nomic-embed-text",
    input=["the quick brown fox", "jumps over the lazy dog"],
)
print(result.data[0].embedding[:5])

import Pendra from 'pendra';

const client = new Pendra();
const result = await client.embeddings.create({
  model: 'nomic-embed-text',
  input: ['the quick brown fox', 'jumps over the lazy dog'],
});
console.log(result.data[0].embedding.slice(0, 5));

200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0131, -0.0442, 0.0921]
    },
    {
      "object": "embedding",
      "index": 1,
      "embedding": [0.0204, -0.0118, 0.0815]
    }
  ],
  "model": "nomic-embed-text",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}

New to embeddings? Start with the Embeddings guide. This page is the field-by-field reference.

Body application/json

model string required

Embedding model ID. List the options at /models?type=embedding.

input string | string[] required

A single string, or an array of strings to embed in one request.

encoding_format string default: float

float returns vectors as JSON arrays; base64 packs them into a smaller string for big batches.

dimensions integer

Requested output dimensionality, for models that support truncation (e.g. Matryoshka embeddings).

Response

An OpenAI-shaped list envelope. data holds one embedding per input string, preserving input order via index — see the example response.

Notes

A request can run up to ~30 minutes, but a single call should be far faster — batch large workloads in groups of a few hundred strings rather than one huge request.
Embedding dimensionality and similarity scaling depend on the model — check the model catalogue.
Embedding requests appear under Embeddings in the console usage view.