github.com/pollinations/pollinations @main

<img src="https://github.com/pollinations/pollinations/raw/main/assets/logo-text-black.svg" alt="pollinations.ai" width="100%" />

Open-source AI for people who make things.

Website · Dashboard · API Docs · Discord

🆕 Recent Apps

Browse all apps →

🚀 New Unified API — Now Live

We've launched https://gen.pollinations.ai — a single endpoint for all your AI generation needs: text, images, audio, video — all in one place.

What's New

• Unified endpoint — single API at gen.pollinations.ai for all generation
• Pollen credits — simple pay-as-you-go system ($1 ≈ 1 Pollen)
• All models, one place — Flux, GPT-5, Claude, Gemini, Seedream, and more
• API keys — publishable keys for frontend, secret keys for backend
• CLI — npx @pollinations/cli for humans and AI agents (source)

Get started at enter.pollinations.ai and check out the API docs

🆕 Latest News

• 2026-07-03 – 🤖 Flow Linnom A new multi-model chat interface joins the community directory. For when querying just one LLM isn't enough. Try it
• 2026-07-02 – 🚀 3D Generation API Send a text prompt to /3d/{prompt}, get a downloadable GLB file back. Powered by Trellis 2 and Rodin 2.5. API Docs
• 2026-07-02 – ⚡ RTX 5090s for Flux Image generation now routes to a self-hosted 5090 pool. Median generation time for 1024x1024 is down to 2.25s. Try it
• 2026-07-02 – 🔗 OAuth 2.1 Support Build apps that authenticate users without touching raw API keys. Standard authorization-code grant with PKCE is now live. Dashboard
• 2026-06-29 – 🚀 Community Text Endpoints Bring your own brain. Register and monetize your own OpenAI-compatible models via the dashboard, or query the new decentralized registry of community-run AI at community/{username}/{model-id}.
• 2026-06-28 – 🩺 Real-time Model Health Added GET /v1/models/status so you can programmatically check if a model is awake before throwing requests at it. Cached for 60 seconds. Check the API Docs.
• 2026-06-28 – 🪙 Get Paid to Ship The 'App Listed' quest is live. Build something, get it listed in the public directory, and earn Pollen directly to your wallet.
• 2026-06-28 – 🧩 Prompt Your Own Puzzles PolliCross uses our image API to generate playable Picross/Nonogram levels from whatever text prompt you can think of. Try it
• 2026-06-28 – 📖 Inpainted Storybooks Storiva is a clever Android app that uses AI inpainting to seamlessly put a child's face into custom-generated story illustrations. Try it
• 2026-06-28 – 🌍 World Weaver A tool that orchestrates text, image, and video models through our unified API to generate entire environments at once. View repo

🌱 Introduction

pollinations.ai is an open-source generative AI platform based in Berlin, powering 500+ community projects with accessible text, image, video, and audio generation APIs. We build in the open and keep AI accessible to everyone—thanks to our amazing supporters.

🚀 Key Features

• 🔓 100% Open Source — code, decisions, roadmap all public
• 🤝 Community-Built — 500+ projects already using our APIs
• 🌱 Pollen Quests — earn Pollen by completing Quests (in alpha)
• 🖼️ Image Generation — Flux, GPT Image, Seedream, Kontext
• 🎬 Video Generation — Seedance, Veo (alpha)
• 🎵 Audio — Text-to-speech and speech-to-text
• 🎣 Easy-to-use Packages (Packages)

Quick Start (3 Steps)

1️⃣ Get your API key
Sign up at enter.pollinations.ai to generate your key.

2️⃣ Choose what you want to generate
Pollinations supports: - 🖼 Images
- 📝 Text
- 🔊 Audio
- 🎬 Video

3️⃣ Make your first request
Use one of the examples below to generate your first AI output in seconds.

🚀 Getting Started

Image Generation

curl 'https://gen.pollinations.ai/image/a%20beautiful%20sunset' -o image.jpg

Or visit pollinations.ai for an interactive experience.

Text Generation

curl 'https://gen.pollinations.ai/text/Hello%20world'

Audio Generation

Simple GET endpoint:

curl 'https://gen.pollinations.ai/audio/Hello%20from%20Pollinations?voice=nova&key=YOUR_API_KEY' -o speech.mp3

OpenAI TTS compatible:

curl 'https://gen.pollinations.ai/v1/audio/speech' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{"model": "tts-1", "input": "Hello from Pollinations!", "voice": "nova"}' \
  -o speech.mp3

Available voices: alloy, echo, fable, onyx, nova, shimmer, plus 30+ ElevenLabs voices.

MCP Server for AI Assistants

Our MCP (Model Context Protocol) server enables AI assistants like Claude to generate images and audio directly. Learn more

Configuration

Add this to your MCP client configuration:

{
  "mcpServers": {
    "pollinations": {
      "command": "npx",
      "args": ["@pollinations/mcp"]
    }
  }
}

Run with npx (no installation required)

npx @pollinations/mcp

Community alternatives like MCPollinations and Sequa MCP Server are also available.

AI assistants can:

• Generate images from text descriptions
• Create text-to-speech audio with various voice options
• Play audio responses through the system speakers
• Access all pollinations.ai models and services
• List available models, voices, and capabilities

For more advanced usage, check out our API documentation.

🔐 Authentication

Get your API key at enter.pollinations.ai

Key Types

⚠️ Publishable keys: Turnstile protection coming soon. Not recommended for production yet.

⚠️ Never expose sk_ keys in client-side code, git repos, or public URLs

💡 Building an app? Use Bring Your Own Pollen — users pay for their own usage, you pay $0

Model Restrictions

Each API key can be scoped to specific models. When creating a key at enter.pollinations.ai, you can:

• Allow all models — key works with any available model
• Restrict to specific models — select exactly which models the key can access (e.g., only flux and openai, or just gptimage-large)

Usage

curl 'https://gen.pollinations.ai/image/a%20cat?key=YOUR_KEY'

Environment variable (best practice):

export POLLINATIONS_API_KEY=sk_...

See full API docs for detailed authentication information.

🖥️ How to Use

Web Interface

Our web interface is user-friendly and doesn't require any technical knowledge. Simply visit https://pollinations.ai and start creating!

API

Use our API directly in your browser or applications:

https://pollinations.ai/p/a_cozy_pixel_art_robot_and_bee_in_a_digital_garden_8-bit_warm_stardew_valley_vibes

Replace the description with your own, and you'll get a unique image based on your words!

Here's an example of a generated image:

🎨 Examples

Image Generation

Python code to download the generated image:

import requests

def download_image(prompt):
    url = f"https://pollinations.ai/p/{prompt}"
    response = requests.get(url)
    with open('generated_image.jpg', 'wb') as file:
        file.write(response.content)
    print('Image downloaded!')

download_image("a_cozy_pixel_art_robot_and_bee_in_a_digital_garden_8-bit_warm_stardew_valley_vibes")

Text Generation

To generate text:

https://gen.pollinations.ai/text/What%20is%20artificial%20intelligence?

Audio Generation

Generate speech from text:

https://gen.pollinations.ai/audio/Hello%20from%20Pollinations?voice=alloy&key=YOUR_API_KEY

Or use the OpenAI TTS-compatible endpoint:

curl 'https://gen.pollinations.ai/v1/audio/speech' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{"model": "tts-1", "input": "Hello from Pollinations!", "voice": "alloy"}' \
  -o speech.mp3

🛠️ Integration

SDK

Check out our Pollinations SDK for Node.js, browser, and React integration.

Architecture

```mermaid %%{init: {'theme': 'dark', 'themeVariables': { 'background': '#1a1a1a', 'primaryColor': '#2a2a2a', 'primaryBorderColor': '#555555', 'primaryTextColor': '#eeeeee', 'lineColor': '#00e5ff', 'clusterBkg': 'transparent', 'clusterBorder': '#888888', 'fontSize': '13px', 'fontFamily': 'Inter, system-