Create embeddings

POST/embeddings

Turns one text or many into vectors, in OpenAI's format: one vector per input, in the order you sent them. Same key, same credit as chat; only input tokens are billed.

Catalogue checked on 20 Oct 2026

SoonOpening soon: what follows describes the service as it will work.

Server URLhttps://evanesca.app/api/v1

POST/embeddingsOpens at launch

AuthorizationBearer $EVANESCA_API_KEY

Headers

Authorizationstringrequired
Bearer followed by your key, which starts with sk-eva-.
Content-Typestringrequired
application/json: the body is JSON.

Request body

application/json

modelstringrequired
An embedding model. Chat and embedding models are separate lists: a chat model sent here answers 404, and so does an embedding model sent to /chat/completions.
Valuesqwen3-embedding-8bbge-multilingual-gemma2
inputstring | array of stringsrequired
One text or an array of texts, each within the model's context window (the models).

Where it runs, what it costs

Evanesca · on the record

Runs in: Scaleway · Paris, Franceqwen3-embedding-8b, bge-multilingual-gemma2
Operator keeps: Scaleway may keep and read requests that cause errors or look abusive, for up to 14 days (Scaleway's data privacy page).
Costs: Per million input tokens, VAT included — no output price: qwen3-embedding-8b €0.168, bge-multilingual-gemma2 €0.168.
Response headers: x-evanesca-operator: scaleway
x-evanesca-location: paris

Search and RAG

Keep the same model for indexing and for queries: vectors from two different models cannot be compared. How to choose a model, its dimensions and the RAG pattern: Embeddings.

Errors

Status	type	Meaning
400	`invalid_request`	The body is not valid JSON, or model or input is missing.
401	`invalid_api_key`	No key, a malformed key, or a revoked one.
402	`insufficient_credit`	Your credit is at zero or below. Add credit to continue.
404	`model_not_found`	Unknown ID, a model Evanesca does not serve, or a chat model sent here.
502	`upstream_error`	The operator could not be reached, sent an unreadable answer, or turned down Evanesca's own account. Your key is not the problem: retry.

Other operator errors reach you with its status and body, and Retry-After when it sends one (errors).

curl https://evanesca.app/api/v1/embeddings \
  -H "Authorization: Bearer $EVANESCA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-embedding-8b",
    "input": ["Contract clause 4.2", "Payroll export, March"]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://evanesca.app/api/v1", api_key=os.environ["EVANESCA_API_KEY"])

vectors = client.embeddings.create(
    model="qwen3-embedding-8b",
    input=["Contract clause 4.2", "Payroll export, March"],
)
print(len(vectors.data[0].embedding))  # 4096

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://evanesca.app/api/v1", apiKey: process.env.EVANESCA_API_KEY });

const vectors = await client.embeddings.create({
  model: "qwen3-embedding-8b",
  input: ["Contract clause 4.2", "Payroll export, March"],
});
console.log(vectors.data[0].embedding.length); // 4096

package main

import (
	"fmt"
	"io"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"model": "qwen3-embedding-8b", "input": ["Contract clause 4.2", "Payroll export, March"]}`)
	req, err := http.NewRequest("POST", "https://evanesca.app/api/v1/embeddings", body)
	if err != nil {
		panic(err)
	}
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVANESCA_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	res, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer res.Body.Close()
	out, _ := io.ReadAll(res.Body)
	fmt.Println(res.Status, string(out))
}

{
  "object": "list",
  "model": "qwen3-embedding-8b",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [ … ] },
    { "object": "embedding", "index": 1, "embedding": [ … ] }
  ],
  "usage": { "prompt_tokens": 14, "total_tokens": 14 }
}

{
  "error": {
    "message": "Insufficient credit balance. Add credit to your account to continue.",
    "type": "insufficient_credit"
  }
}