Embeddings

Turns text into vectors for search, clustering, and retrieval, in the OpenAI Embeddings format. Embedding models are paid models from providers: each one's price per million input tokens is on its page at freetheai.org/models.

POSThttps://api.freetheai.org/v1/embeddings

Request

curl

curl https://api.freetheai.org/v1/embeddings \
  -H "Authorization: Bearer $FTAI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "MODEL_ID", "input": ["first text", "second text"]}'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.freetheai.org/v1", api_key=os.environ["FTAI_KEY"])

result = client.embeddings.create(model="MODEL_ID", input=["first text", "second text"])
print(len(result.data[0].embedding))

TypeScript

import OpenAI from 'openai'

const client = new OpenAI({ baseURL: 'https://api.freetheai.org/v1', apiKey: process.env.FTAI_KEY })

const result = await client.embeddings.create({ model: 'MODEL_ID', input: ['first text', 'second text'] })
console.log(result.data[0].embedding.length)

Field	Type	Description
model	string	An embedding model ID from GET /v1/models ("type": "embeddings").
input	string or array	One text, a list of texts, or token arrays.
dimensions	integer	Optional. Fewer dimensions, for models that support it (1 to 65536).
encoding_format	string	Optional. float (default) or base64.

Other fields are not sent to the model.

Response

{
  "object": "list",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0123, -0.0456] },
    { "object": "embedding", "index": 1, "embedding": [0.0789, 0.0012] }
  ],
  "model": "MODEL_ID",
  "usage": { "prompt_tokens": 6, "total_tokens": 6 }
}

You are charged for usage.prompt_tokens at the model's input price. The request first holds an estimate on your wallet; the unused part is given back.

Errors

Status	Meaning
400	A field has a value the endpoint does not take (the message names it).
401	Missing or invalid API key.
402	Not enough wallet balance, or the key's budget is used (paid usage errors).
404	No model has that ID, or none of the providers you follow serve it.
502 / 503	The provider failed or is busy. Retry; a failed request is not charged.