SDKs & Libraries

Install a library or use the OpenAI SDK you already have.

Overview

Fluxpool's API is OpenAI-compatible. Three ways to integrate:

OpenAI SDK Recommended

Use the official OpenAI Python or Node.js SDK. Change base_url to api.fluxpool.ai/v1. Done.

Best for: Teams already using OpenAI.
Fluxpool Python SDK

Lightweight wrapper with Fluxpool-specific features: credit balance, model listing, webhook helpers.

Best for: Python developers wanting Fluxpool-native DX.
Fluxpool Node.js SDK

Same Fluxpool-native features for the Node/TypeScript ecosystem.

Best for: Node.js / TypeScript developers.

OpenAI SDK

Recommended

Already using the OpenAI SDK? Change one line. Access 15+ image and video models.

Installation

If you don't have the OpenAI SDK installed yet:

bash 
pip install openai

Requires openai >= 1.0.0 (Python) or openai >= 4.0.0 (Node.js).

Image Generation

python 
from openai import OpenAI

client = OpenAI(
    base_url="https://api.fluxpool.ai/v1",  # ← Only change
    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, 8K",
    size="1024x1024"
)

print(response.data[0].url)

Replace fp_your_api_key with your actual API key. Get your API key →

Video Generation

Video generation is async. Submit a job, receive results via webhook or polling.

python 
from openai import OpenAI

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

# Submit video generation job
response = client.chat.completions.create(
    model="wan-video-2.1",
    messages=[{
        "role": "user",
        "content": "A drone shot flying through cherry blossom trees, slow motion"
    }],
    extra_body={
        "type": "video",
        "duration": 5,
        "resolution": "1280x720",
        "webhook_url": "https://your-app.com/webhook"  # Optional
    }
)

job_id = response.id
print(f"Job submitted: {job_id}")
python 
import time

# Poll for completion
while True:
    status = client.chat.completions.retrieve(job_id)
    if status.status == "completed":
        print(status.data[0].url)  # Video URL
        break
    elif status.status == "failed":
        print(f"Error: {status.error}")
        break
    time.sleep(5)  # Check every 5 seconds

For production use, we recommend webhooks over polling. Webhook setup guide →

Fluxpool Python SDK

Fluxpool-native SDK with credit balance, model listing, and webhook helpers.

fluxpool/fluxpool-python PyPI: fluxpool Python 3.8+

Installation

bash 
pip install fluxpool

Image Generation

python 
from fluxpool import Fluxpool

fp = Fluxpool(api_key="fp_your_api_key")

# Generate an image
image = fp.images.generate(
    model="flux-1.1-pro",
    prompt="Isometric game village with tavern and market, pixel art",
    size="1024x1024"
)

print(image.url)
print(f"Credits remaining: {image.credits_remaining}")

The SDK automatically returns your remaining credit balance with every response.

Video Generation

python 
# Generate a video (async)
job = fp.videos.generate(
    model="wan-video-2.1",
    prompt="Timelapse of a cyberpunk city being built, aerial view",
    duration=5,
    resolution="1280x720"
)

# Wait for completion (blocking helper)
result = job.wait()
print(result.url)

Additional Features

python 
# Check credit balance
balance = fp.credits.balance()
print(f"Credits: {balance.remaining}")

# List available models
models = fp.models.list()
for model in models:
    print(f"{model.id} — {model.type} — ${model.cost_per_generation}")

# List your recent generations
history = fp.generations.list(limit=10)

Full SDK reference → GitHub README

Fluxpool Node.js SDK

TypeScript-first. Same Fluxpool-native features for Node.js and edge runtimes.

fluxpool/fluxpool-node npm: fluxpool Node 18+ TypeScript

Installation

bash 
npm install fluxpool
alternatives 
yarn add fluxpool
# or
pnpm add fluxpool

Image Generation

typescript 
import { Fluxpool } from "fluxpool";

const fp = new Fluxpool({ apiKey: "fp_your_api_key" });

const image = await fp.images.generate({
  model: "qwen-image-3-6-plus",
  prompt: "Anime warrior princess in bamboo forest, Studio Ghibli style",
  size: "1024x1024",
});

console.log(image.url);
console.log(`Credits remaining: ${image.creditsRemaining}`);

Video Generation

typescript 
// Generate a video (async)
const job = await fp.videos.generate({
  model: "kling-v2",
  prompt: "A koi fish transforming into a phoenix, slow motion, cinematic",
  duration: 5,
  resolution: "1080p",
});

// Wait for completion
const result = await job.wait();
console.log(result.url);

Additional Features

typescript 
// Check credit balance
const balance = await fp.credits.balance();
console.log(`Credits: ${balance.remaining}`);

// List available models
const models = await fp.models.list();
models.forEach(m => console.log(`${m.id} — ${m.type} — $${m.costPerGeneration}`));

// With TypeScript — full type safety
import type { ImageGenerateParams, VideoGenerateParams } from "fluxpool";

Full SDK reference → GitHub README

Community SDKs

Community-maintained libraries. Not officially supported.

Language Package Maintainer Link
Go fluxpool-go @community GitHub →
Ruby fluxpool-ruby @community GitHub →
Rust fluxpool-rs @community GitHub →
PHP fluxpool-php @community GitHub →

The OpenAI-compatible REST API works from any language that can make HTTP requests. See the API Reference →

REST API

No SDK needed. Any HTTP client works.

curl 
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": "Product photo of sneakers on marble, studio lighting",
    "size": "1024x1024"
  }'

Base URL: https://api.fluxpool.ai/v1

Auth: Bearer token in Authorization header.

Format: JSON request and response bodies.

Full API Reference →

Need help?

→ Quickstart guide — generate your first image in 2 minutes → API Reference — full endpoint documentation → Discord — ask the community
Try the playground →