Create images

POST/images/generations

Turns a prompt into images with FLUX.1 [schnell], in OpenAI's format: the official SDKs work as they are (client.images.generate). Images come back as JPEG, base64-encoded; Evanesca hosts and keeps none of them.

Catalogue checked on 20 Oct 2026

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

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

POST/images/generationsOpens 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
FLUX.1 [schnell], by Black Forest Labs (Germany).
Valuesflux-schnell
promptstringrequired
The description of the image, 400 characters at most.
ninteger
How many images to make.
Default1
Values1–5
sizestring
The size of each image, in pixels.
Default1024x1024
Values1024x10241792x10241024x1792
response_formatstring
b64_json puts each image in data[].b64_json; url returns a data URL rather than a link, since Evanesca hosts no image.
Defaultb64_json
Valuesb64_jsonurl

Where it runs, what it costs

Evanesca · on the record

Runs in: Infomaniak · Switzerlandflux-schnell
Operator keeps: Infomaniak states that queries are “neither recorded nor used to train models” (Infomaniak AI Tools).
Costs: €0.0092 per second of generation, VAT included, rounded up to the next second, one second at least; usage.generation_seconds is what is billed. About 2 seconds, so about €0.02, for a typical FLUX.1 [schnell] image. A refused request costs nothing.
Response headers: x-evanesca-operator: infomaniak
x-evanesca-location: switzerland

What leaves Evanesca

The prompt go to Infomaniak, in Switzerland — outside the EU, under an EU adequacy decision; the images come back in the response and Evanesca keeps none of them. The images carry IPTC metadata marking them as AI-generated (AI Act, art. 50(2)) — metadata, not a watermark, so a screenshot or a re-encode can remove it (Images).

Errors

Status	type	Meaning
400	`invalid_request`	A prompt missing or over 400 characters, n outside 1 to 5, a size not in the list, or a multipart body — the param field says which (limits).
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 photomaker-v2, which is served by /images/edits.
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/images/generations \
  -H "Authorization: Bearer $EVANESCA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-schnell",
    "prompt": "A lighthouse at dusk, watercolour",
    "size": "1024x1024"
  }'

import base64, os
from openai import OpenAI

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

result = client.images.generate(
    model="flux-schnell",
    prompt="A lighthouse at dusk, watercolour",
    size="1792x1024",
)
with open("image.jpg", "wb") as f:
    f.write(base64.b64decode(result.data[0].b64_json))

import { writeFile } from "node:fs/promises";
import OpenAI from "openai";

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

const result = await client.images.generate({
  model: "flux-schnell",
  prompt: "A lighthouse at dusk, watercolour",
  size: "1792x1024",
});
await writeFile("image.jpg", Buffer.from(result.data[0].b64_json, "base64"));

package main

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

func main() {
	body := strings.NewReader(`{"model": "flux-schnell", "prompt": "A lighthouse at dusk, watercolour", "size": "1024x1024"}`)
	req, err := http.NewRequest("POST", "https://evanesca.app/api/v1/images/generations", 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))
}

{
  "created": 1791763200,
  "model": "flux-schnell",
  "data": [{ "b64_json": "/9j/4AAQSkZJRgABAQ…" }],
  "usage": { "generation_seconds": 2, "images": 1 }
}

{
  "error": {
    "message": "'size' must be one of: 1024x1024, 1792x1024, 1024x1792. Nothing was charged.",
    "type": "invalid_request",
    "param": "size"
  }
}