Text-to-Image API Reference

FLUX text-to-image API reference and live debugger — full FLUX.2 [klein/pro/max/flex] family via OpenAI-compatible drop-in, 4MP output and exact hex color control

POST /v1/images/generations

Generate an image from a text prompt

cURL

curl --request POST \
  --url https://api.apiyi.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "flux-2-pro",
  "prompt": "A cinematic shot of a futuristic city at sunset, 85mm lens"
}
'

import requests

url = "https://api.apiyi.com/v1/images/generations"

payload = {
    "model": "flux-2-pro",
    "prompt": "A cinematic shot of a futuristic city at sunset, 85mm lens"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'flux-2-pro',
    prompt: 'A cinematic shot of a futuristic city at sunset, 85mm lens'
  })
};

fetch('https://api.apiyi.com/v1/images/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.apiyi.com/v1/images/generations",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'flux-2-pro',
    'prompt' => 'A cinematic shot of a futuristic city at sunset, 85mm lens'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.apiyi.com/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"flux-2-pro\",\n  \"prompt\": \"A cinematic shot of a futuristic city at sunset, 85mm lens\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.apiyi.com/v1/images/generations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"flux-2-pro\",\n  \"prompt\": \"A cinematic shot of a futuristic city at sunset, 85mm lens\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.apiyi.com/v1/images/generations")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"flux-2-pro\",\n  \"prompt\": \"A cinematic shot of a futuristic city at sunset, 85mm lens\"\n}"

response = http.request(request)
puts response.read_body

200

{
  "created": 1776832476,
  "data": [
    {
      "url": "https://delivery-eu.bfl.ai/results/xxx/sample.jpeg?signature=..."
    }
  ]
}

The interactive Playground on the right supports live debugging. Fill in your API Key in the Authorization header (format: Bearer sk-xxx), choose model and size, enter the prompt, and send.

Use this page for “text generates image” — only a prompt is needed, no upload. For editing or multi-reference fusion of existing images, see the Image Editing endpoint.

⚠️ Key differences / unsupported parameters

• Result URL is valid for only 10 minutes — data[0].url must be downloaded immediately, expired URLs return 404
• width / height must be multiples of 16 — otherwise returns 400
• prompt_upsampling is not supported on FLUX.2 [klein] — silently ignored
• Total pixel cap is 4MP (~2048×2048) — exceeding returns 400
• grounding search only on flux-2-max — other models will not trigger live search even with time-sensitive prompts

All image APIs are synchronous — there is no task ID to poll, and if your client disconnects the result is lost while the request is still billed. Set a generous timeout for this model; see Image API Essentials & Best Practices.

Code Examples

Python (OpenAI SDK Drop-in)

from openai import OpenAI
import requests

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.apiyi.com/v1"
)

resp = client.images.generate(
    model="flux-2-pro",
    prompt="A cinematic shot of a futuristic city at sunset, 85mm lens, hyper-realistic",
    size="1920x1080"
)

# data[0].url is valid for only 10 minutes — download immediately
image_url = resp.data[0].url
with open("out.jpg", "wb") as f:
    f.write(requests.get(image_url, timeout=30).content)

Python (Native requests · with width/height syntax)

import requests

API_KEY = "sk-your-api-key"

response = requests.post(
    "https://api.apiyi.com/v1/images/generations",
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    },
    json={
        "model": "flux-2-max",
        "prompt": "Score of yesterday's Champions League final, infographic style",
        "width": 1920,
        "height": 1080,
        "safety_tolerance": 2,
        "output_format": "jpeg",
        "seed": 42
    },
    timeout=120
).json()

image_url = response["data"][0]["url"]
with open("out.jpg", "wb") as f:
    f.write(requests.get(image_url, timeout=30).content)

cURL

curl -X POST "https://api.apiyi.com/v1/images/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-pro",
    "prompt": "Luxury eyeshadow palette with 6 pans: top row #B76E79, #E8D5B7, #8B4789; bottom row #CD7F32, #F8F6F0, #800020",
    "size": "1024x1024",
    "output_format": "png"
  }'

Node.js (Native fetch)

import fs from 'node:fs';

const resp = await fetch('https://api.apiyi.com/v1/images/generations', {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json',
        'Authorization': 'Bearer sk-your-api-key'
    },
    body: JSON.stringify({
        model: 'flux-2-klein-9b',
        prompt: 'A serene mountain landscape at golden hour, soft diffused light',
        width: 1024,
        height: 1024
    })
});

const { data } = await resp.json();
// Download immediately — URL expires in 10 minutes
const img = await fetch(data[0].url);
fs.writeFileSync('out.jpg', Buffer.from(await img.arrayBuffer()));

Browser JavaScript (direct render)

{/* Demo only — production should proxy via backend to avoid leaking the key. The delivery URL has CORS disabled, so server-side download to your own CDN is recommended. */}
const resp = await fetch('https://api.apiyi.com/v1/images/generations', {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json',
        'Authorization': 'Bearer sk-your-api-key'
    },
    body: JSON.stringify({
        model: 'flux-2-pro',
        prompt: 'Watercolor aurora borealis over Nordic mountains',
        size: '1536x1024'
    })
});

const { data } = await resp.json();
{/* delivery URL has CORS disabled, but <img src> works for direct rendering. Server-side download is still recommended for production. */}
document.getElementById('img').src = data[0].url;

Parameter Reference

Parameter	Type	Required	Default	Description
model	string	Yes	—	FLUX model ID, see table below
prompt	string	Yes	—	Prompt, up to 32K tokens. Supports natural language and structured JSON
size	string	No	1024x1024	OpenAI-style size string, e.g., 1920x1080
width	integer	No	1024	BFL-native, alternative to size, must be multiple of 16
height	integer	No	1024	BFL-native, must be multiple of 16
seed	integer	No	random	Fix for reproducibility
safety_tolerance	integer	No	2	0 (strictest) – 6 (most permissive)
output_format	string	No	jpeg	jpeg / png
prompt_upsampling	boolean	No	false	Auto-expand prompt (not on [klein])
steps	integer	No	50	Only for flux-2-flex, max 50
guidance	number	No	4.5	Only for flux-2-flex, 1.5–10
n	integer	No	1	Only 1 supported

Supported Model IDs

Model ID	Speed	Best For
flux-2-max	< 15s	Flagship + grounding search
flux-2-pro	< 10s	Production at scale, best value
flux-2-flex	Slower	Typography specialist
flux-2-klein-9b	Sub-second	Balanced
flux-2-klein-4b	Sub-second	Fastest
flux-pro-1.1-ultra	~10s	Legacy 4MP (see Historical Versions)
flux-pro-1.1	~5s	Legacy 1.6MP
flux-pro	~6s	First-gen pro
flux-dev	~5s	Dev/test

Detailed constraints, allowed values, and examples are visible in the right-side Playground field hints. All enum fields support dropdown selection.

Response Format

{
    "created": 1776832476,
    "data": [
        {
            "url": "https://delivery-eu.bfl.ai/results/xxx/sample.jpeg?signature=..."
        }
    ]
}

⚠️ data[0].url is valid for only 10 minutes

• URL hosted on delivery-eu.bfl.ai / delivery-us.bfl.ai, signature expires after 10 min
• CORS is disabled — browser fetch is blocked, but <img src> rendering works
• Production services must server-side download to your own OSS / CDN
• Unlike OpenAI’s gpt-image-2 (which returns b64_json), FLUX returns URL only — no base64.

FLUX does not return a usage field (priced per image, not per token). Actual billing follows the pricing table on this site. The response header x-request-id is for support tracing.

Authorizations

Authorization · string · header · required

API Key from the APIYI Console

Body

application/json

model · enum<string> · default: flux-2-pro · required

FLUX model ID. For FLUX.2 prefer flux-2-pro / flux-2-max; legacy versions in the Historical Versions page.

Available options: flux-2-max, flux-2-pro, flux-2-flex, flux-2-klein-9b, flux-2-klein-4b, flux-pro-1.1-ultra, flux-pro-1.1, flux-pro, flux-dev

prompt · string · required

Prompt, up to 32K tokens. Supports natural language, hex codes, and structured JSON.

Example:

"A cinematic shot of a futuristic city at sunset, 85mm lens"

size · string · default: 1024x1024

OpenAI-style size string. Pick either size or width+height. Common: 1024x1024 / 1536x1024 / 1024x1536 / 1920x1080 / 1440x2048 / 2048x2048. Custom must satisfy: multiples of 16, 64×64–4MP.

Example:

"1920x1080"

width · integer · default: 1024

BFL-native syntax, alternative to size. Must be a multiple of 16, between 64 and 2048.

Required range: 64 <= x <= 2048

Example:

1920

height · integer · default: 1024

BFL-native syntax. Must be a multiple of 16, between 64 and 2048.

Required range: 64 <= x <= 2048

Example:

1080

seed · integer

Fix for reproducibility — same seed + same other params yields the same result.

Example:

42

safety_tolerance · integer · default: 2

Moderation level. 0 = strictest, 6 = most permissive, default 2.

Required range: 0 <= x <= 6

output_format · enum<string> · default: jpeg

Output format.

Available options: jpeg, png

prompt_upsampling · boolean · default: false

Auto-expand the prompt. Not supported on FLUX.2 [klein] (silently ignored).

steps · integer · default: 50

Only flux-2-flex. Inference steps, max 50.

Required range: 1 <= x <= 50

guidance · number · default: 4.5

Only flux-2-flex. Guidance scale. 1.5–10, higher = closer to prompt.

Required range: 1.5 <= x <= 10

n · enum<integer> · default: 1

Number of images. Only 1 supported.

Available options: 1

Response

200

application/json

Image generated

created · integer

Unix timestamp

Example:

1776832476

data · object[]

Result array (single image per call)

Show child attributes