Quickstart

Generate your first image in 2 minutes.

Prerequisites

• A Fluxpool.ai account (free — includes 50 credits)
• Python 3.8+ or Node.js 18+ (or any HTTP client for cURL)

Step 1: Get your API key

Sign in to the Fluxpool app, open API / MCP Access, and click Create new key. Copy the key immediately — the full value is shown only once.

Your API key starts with fp_live_ followed by 40 hex characters. Keep it secret. Never commit it to version control or expose it in browser code.

app.fluxpool.ai — API / MCP Access

Your API Key

fp_live_a1b2c3d4•••••••••••••••••••••••••••••••••

→ Open API / MCP Access

Step 2: Install the SDK

Fluxpool uses an OpenAI-compatible API. Use the official OpenAI SDK — just change the base URL.

pip install openai

npm install openai

No installation needed. cURL is available on most systems.

Already using the OpenAI SDK? You're ready. Skip to Step 3.

Step 3: Generate an image

Eight lines of code. One image back.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.fluxpool.ai/v1",
    api_key="fp_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
)

response = client.images.generate(
    model="flux-2-pro",
    prompt="A dragon perched on a neon-lit Tokyo rooftop at midnight, cinematic lighting, 8K",
    size="1024x1024"
)

print(response.data[0].url)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.fluxpool.ai/v1",
  apiKey: "fp_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
});

const response = await client.images.generate({
  model: "flux-2-pro",
  prompt: "A dragon perched on a neon-lit Tokyo rooftop at midnight, cinematic lighting, 8K",
  size: "1024x1024",
});

console.log(response.data[0].url);

curl https://api.fluxpool.ai/v1/images/generations \
  -H "Authorization: Bearer fp_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-pro",
    "prompt": "A dragon perched on a neon-lit Tokyo rooftop at midnight, cinematic lighting, 8K",
    "size": "1024x1024"
  }'

Response

{
  "created": 1717200000,
  "data": [
    {
      "url": "https://cdn.fluxpool.ai/generations/abc123.png",
      "revised_prompt": null
    }
  ]
}

"A dragon on a neon-lit Tokyo rooftop, 8K"

flux-2-pro

Generated with flux-2-pro · 1024×1024 · ~3 seconds

💡

Try different models by changing the model parameter. See all available models →

Step 4: Generate a video

Video generation is async. Submit a request, then poll the returned presigned URL (or the generation status endpoint) until the file is ready.

import time
import requests

API_KEY = "fp_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
headers = {"Authorization": f"Bearer {API_KEY}"}

# Submit video generation request
response = requests.post(
    "https://api.fluxpool.ai/v1/videos/generations",
    headers=headers,
    json={
        "model": "seedance-v2",
        "prompt": "A koi fish transforming into a phoenix, slow motion, cinematic",
        "resolution": "720p",
        "duration": 5
    }
).json()

generation_id = response["id"]
video_url = response["data"][0]["url"]  # S3 presigned URL (valid 1h)

# Poll the generation-status endpoint (or the presigned URL directly)
while True:
    status = requests.get(
        f"https://api.fluxpool.ai/v1/generations/{generation_id}",
        headers=headers
    ).json()

    if status["status"] == "completed":
        print(status["data"][0]["url"])
        break

    time.sleep(3)

const API_KEY = "fp_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx";
const headers = {
  Authorization: `Bearer ${API_KEY}`,
  "Content-Type": "application/json",
};

// Submit video generation request
const submitRes = await fetch("https://api.fluxpool.ai/v1/videos/generations", {
  method: "POST",
  headers,
  body: JSON.stringify({
    model: "seedance-v2",
    prompt: "A koi fish transforming into a phoenix, slow motion, cinematic",
    resolution: "720p",
    duration: 5,
  }),
});
const submission = await submitRes.json();
const generationId = submission.id;

// Poll the generation-status endpoint until the video is ready
while (true) {
  const res = await fetch(
    `https://api.fluxpool.ai/v1/generations/${generationId}`,
    { headers }
  );
  const status = await res.json();
  if (status.status === "completed") {
    console.log(status.data[0].url);
    break;
  }
  await new Promise((r) => setTimeout(r, 3000));
}

# Submit video generation
curl https://api.fluxpool.ai/v1/videos/generations \
  -H "Authorization: Bearer fp_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-v2",
    "prompt": "A koi fish transforming into a phoenix, slow motion, cinematic",
    "resolution": "720p",
    "duration": 5
  }'

# Response includes a generation_id — poll the status endpoint:
curl https://api.fluxpool.ai/v1/generations/{generation_id} \
  -H "Authorization: Bearer fp_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

⏱

Video generation takes 30–90 seconds depending on the model and duration. Poll /v1/generations/{id} or the presigned S3 URL every few seconds. Webhook delivery is on the roadmap. Learn more →

VIDEO

seedance-v2

Generated with seedance-v2 · 1280×720 · 5 seconds

Step 5: Switch models in one line

Change the model parameter. That's it. Same API, same format, different model.

The authoritative list of available models is served by the API itself — call GET /v1/models to fetch what you can call today, then pass any returned id as the model parameter. Two verified examples to start with:

Model	Type	Endpoint
`flux-2-pro`	Image	/v1/images/generations
`seedance-v2`	Video	/v1/videos/generations

→ Full model reference (with GET /v1/models)

Switch models in one line:

# Just change the model parameter
response = client.images.generate(
    model="qwen-image-max",  # ← changed from "flux-2-pro"
    prompt="Anime warrior princess in bamboo forest, Studio Ghibli style",
    size="1024x1024"
)

Next steps

📖

Ready to generate?

Start with a 1-month Trial plan. No credit card required.

Start generating →

Next Authentication →

Quickstart

Prerequisites

Step 1: Get your API key

Step 2: Install the SDK

Step 3: Generate an image

Step 4: Generate a video

Step 5: Switch models in one line

Next steps

Image Generation Docs

Video Generation Docs

Authentication

Try the Playground

Ready to generate?