Embeddings

Turn text into vectors for semantic search, clustering, deduplication and retrieval-augmented generation (RAG). The endpoint has the same shape as OpenAI's POST /embeddings, so client.embeddings.create(...) works unchanged.

POST https://api14.com/api/v1/embeddings

Request

Example

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.embeddings.create({
  "model": "openai/text-embedding-3-small",
  "input": [
    "The quick brown fox",
    "Lorem ipsum"
  ]
});
console.log(result.data.map((d) => d.embedding.length));

Response

{
  "object": "list",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0023, -0.0091, 0.0154, "..."] }
  ],
  "model": "openai/text-embedding-3-small",
  "usage": { "prompt_tokens": 8, "total_tokens": 8, "cost": 0.00000016 }
}

data[i].index matches the position of the input in your input array.

Choosing a model

List embeddings models with their prices, without an API key:

curl https://api14.com/api/v1/embeddings/models
# or, with categories and our prices:
curl "https://api14.com/api/v1/models?category=embeddings"

Vectors from different models are not comparable. Store the model id next to every vector and re-embed your corpus when you switch models.

Pricing

Embeddings are billed per input token at the model's listed price, shown as "$ / 1M tokens". The cost of each request is returned in usage.cost (USD) and debited from your balance. See Pricing & billing.

Tips

• Batch inputs: one request with 100 strings is faster and counts as one request against your rate limit.
• Keep each input under the model's context length; longer text is rejected upstream.
• Normalize vectors (most models already return unit length) and use cosine similarity.

Errors

Full list: Errors.