Pollinations.AI

• 🔐 Auth Dashboard - New authentication dashboard is now live! Visit auth.pollinations.ai to manage your API tokens and referrer domains for priority access. Learn more.
• 🏆 User Tier System - Apps automatically upgrade through seed/flower/nectar tiers based on usage and ad integration. Higher tiers unlock unlimited usage, SOTA models, and revenue sharing. Learn more.
• 🔍 Special Bee - Request flower tier upgrade for unlimited usage and SOTA models! Submit a Special Bee Request or use auth.pollinations.ai. More info
• 📚 API Documentation - Major API documentation improvements! We've completely revamped our API docs with better examples, clearer explanations, and interactive code snippets. Check it out.
• 🤖 MCP Server - New Model Context Protocol (MCP) server for AI assistants like Claude to generate images directly! Learn more.
  
• 💲 Support Us - You can now support us with our new Tip Us button. Optionally connect your Discord account to Ko-Fi to get premium Discord roles!
• 🎵 Audio Generation - New text-to-speech and speech-to-text capabilities are now available! Try the openai-audio model - see our API documentation for details.
• 🤖 AI Code Assistant - We're excited to announce MentatBot, the autonomous AI coding assistant that implements new features directly from GitHub issues! Simply create an issue describing what you'd like to see, and MentatBot will analyze and implement it. Learn more.
• 🖼️ GPT Image - Introducing our new state-of-the-art text-to-image model, GPT Image, which generates high-resolution, contextually accurate visuals from any prompt. Learn more about OpenAI's latest image generation model here.

Pollinations.AI is an open-source gen AI startup based in Berlin, providing the most easy-to-use, free text and image generation API available. No signups or API keys required. We prioritize your privacy with zero data storage and completely anonymous usage.

• 🔓 100% Open Source
• 🆓 Free to use
• 🔒 Simplicity and privacy: No logins, no keys, no data stored
• 🖼️ Embed like any normal image or text
• 🎵 Audio generation: Text-to-speech and speech-to-text capabilities
• 🌍 Free AI image and text generation APIs
• 🤝 Used by various open-source LLMs, bots, and communities
• 🎣 Easy-to-use React hooks (React Hooks Examples)
• 🤖 Autonomous Development: Features implemented by our MentatBot coding assistant through GitHub issues

1. Visit https://pollinations.ai
2. Type your description in the text box
3. Click "Generate" and watch the magic happen!

1. Visit https://text.pollinations.ai
2. Start chatting with the AI

1. Use the openai-audio model with our API (explore voices at OpenAI.fm)
2. Generate speech from text or transcribe audio to text

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

# Run with npx (no installation required)
npx @pollinations/model-context-protocol

Community alternatives like MCPollinations 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.

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

Use our API directly in your browser or applications:

https://pollinations.ai/p/conceptual_isometric_world_of_pollinations_ai_surreal_hyperrealistic_digital_garden

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:

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("conceptual_isometric_world_of_pollinations_ai_surreal_hyperrealistic_digital_garden")

To generate text, use this URL:

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

To generate audio from text, use this URL:

https://text.pollinations.ai/Welcome%20to%20Pollinations?model=openai-audio&voice=nova

We offer React hooks for easy integration. Example usage:

import React from 'react';
import { usePollinationsImage, usePollinationsText } from '@pollinations/react';
import ReactMarkdown from 'react-markdown';

const AIGeneratedContent = () => {
  const imageUrl = usePollinationsImage("Beautiful landscape of Paris with Eiffel Tower", { width: 800, height: 600, seed: 42 });
  const markdown = usePollinationsText("Write a brief travel guide for Paris, including top attractions and local cuisine in markdown", { seed: 42 });

  return (
    <div>
      <h2>AI-Generated Travel Guide</h2>
      <img src={imageUrl} alt="AI Generated" />
      {markdown ? (
        <ReactMarkdown>{markdown}</ReactMarkdown>
      ) : (
        <p>Loading markdown content...</p>
      )}
    </div>
  );
};

export default AIGeneratedContent;

Check out our Pollinations React Hooks for more details.

graph LR
    Q[Bots - Discord, Telegram, WhatsApp] --> L1
    
    N[30+ Mobile and Web Apps] --> L1
    N --> L2
    
    A[pollinations.ai Web Frontend] --> L1
    A --> L2
    
    R[AI Agents - Qwen, Sillytavern, ...] --> L1
    
    AI[AI Assistants - Claude] --> MCP[MCP Server]
    MCP --> L1
    
    L1[Image CDN] --> CF[Cloudflare Worker with R2 Cache]
    L2[Text CDN] --> C
    
    CF --> B
    
    B[image-origin.pollinations.ai - AWS EC2 CPU] --> F[Azure OpenAI - Prompt Enhancing]
    B --> S[LlamaGuard - Safety Checker]
    F --> E[Translation Service - 1 GPU VM]
    E --> D[FLUX image generation model - 2-6 GPU VMs on AWS]
    
    C[text.pollinations.ai - AWS EC2 CPU] --> P[karma.yt - Realtime News]
    C --> SC[Scaleway API]
    C --> DS[Deepseek API]
    C --> G[Azure-hosted Serverless LLMs]
    C --> CFM[Cloudflare AI]
    SC --> MI[Mistral Models]
    SC --> QW[Qwen Models]
    SC --> LL[Llama Models]
    DS --> DM[Deepseek Models]
    G --> H[OpenAI]
    G --> K[Claude]
    CFM --> CFL[Llama & Deepseek Models]