Quickstart

Generate your first image in 2 minutes.

Prerequisites

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

Step 1: Get your API key

Your API key starts with fp_. Keep it secret. Don't commit it to version control.

dashboard — API Keys

Your API Key

fp_sk-xxxx••••••••••••••xxxx

→ Go to Dashboard

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_your_api_key"
)

response = client.images.generate(
    model="flux-1.1-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_your_api_key",
});

const response = await client.images.generate({
  model: "flux-1.1-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_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-1.1-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-1.1-pro

Generated with flux-1.1-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, get a result via polling or webhook.

import time
import requests
from openai import OpenAI

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

# Submit video generation request
response = client.chat.completions.create(
    model="wan-video-2.1",
    messages=[{
        "role": "user",
        "content": "A koi fish transforming into a phoenix, slow motion, cinematic"
    }],
    extra_body={"video": {"resolution": "1280x720", "duration": 5}}
)

generation_id = response.id

# Poll for completion
while True:
    status = requests.get(
        f"https://api.fluxpool.ai/v1/generations/{generation_id}",
        headers={"Authorization": "Bearer fp_your_api_key"}
    ).json()

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

    time.sleep(5)

import OpenAI from "openai";

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

// Submit video generation request
const response = await client.chat.completions.create({
  model: "wan-video-2.1",
  messages: [{
    role: "user",
    content: "A koi fish transforming into a phoenix, slow motion, cinematic",
  }],
  video: { resolution: "1280x720", duration: 5 },
});

const generationId = response.id;

// Poll for completion
const poll = async () => {
  while (true) {
    const res = await fetch(
      `https://api.fluxpool.ai/v1/generations/${generationId}`,
      { headers: { Authorization: "Bearer fp_your_api_key" } }
    );
    const status = await res.json();
    if (status.status === "completed") {
      console.log(status.output.url);
      return;
    }
    await new Promise((r) => setTimeout(r, 5000));
  }
};
await poll();

# Submit video generation
curl https://api.fluxpool.ai/v1/videos/generations \
  -H "Authorization: Bearer fp_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-video-2.1",
    "prompt": "A koi fish transforming into a phoenix, slow motion, cinematic",
    "resolution": "1280x720",
    "duration": 5
  }'

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

⏱

Video generation takes 30–90 seconds depending on the model and duration. For production use, we recommend webhooks instead of polling. Learn more →

VIDEO

wan-video-2.1

Generated with wan-video-2.1 · 1280×720 · 5 seconds · ~45s generation time

Step 5: Switch models in one line

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

Model	Type	Best For	Cost
flux-1.1-pro	Image	Photorealism, prompt adherence	$0.03/image
qwen-image-3-6-plus	Image	Asian aesthetics, text rendering	$0.02/image
sdxl-1.0	Image	Fast drafts, ControlNet	$0.01/image
wan-video-2.1	Video	Cinematic video, smooth motion	$0.15/video
kling-v2	Video	Character consistency	$0.20/video
runway-gen3	Video	Premium motion, coherence	$0.50/video

→ Browse all 15+ models → Full model parameter reference

Switch from Flux to Qwen in one line:

# Just change the model parameter
response = client.images.generate(
    model="qwen-image-3-6-plus",  # ← changed from "flux-1.1-pro"
    prompt="Anime warrior princess in bamboo forest, Studio Ghibli style",
    size="1024x1024"
)