Computer MCP server

Website · Dashboard · Playground · Guides · API Docs · Discord

🆕 Recent Apps

Name	Description	Author
✍️ Stretchtext for Pollinations	Browser extension that shrinks any page to a short version with Pollinations AI. Click a phrase to grow the original sentence back in place, word for word. Readers pay with their own Pollen.	@tomdacatto
✍️ StretchText	Any page as stretchtext: skim the short version, click a phrase to grow it in place, and each request spends the reader's own Pollen via the device flow. No build step, live model list, tested.	@rekty
🖼️ Pollinations Studio	AI studio using gen.pollinations.ai for batch image generation (up to 10 parallel prompts), custom model selection, and multi-model AI chat with Bring Your Own Pollen (BYOP) authentication.	@lekezoa
🖼️ Tomadix	Tomadix is an AI-powered creative platform designed to help users create professional prompts and generate high-quality images using artificial intelligence. Made with Pollinations.ai.	@gereiz
💬 Parallel Voices	Ask one question to several Pollinations text models at once and compare every answer side by side, with latency and token counts per model. Bring your own Pollen.	@EzzElddin-AbdAllah
💬 DynaSpark AI	DynaSpark AI is a versatile multimodal assistant for text, code, image and video generation, data analysis, and web and document processing, powered by Pollinations AI and BYOP models.	@Th3-C0der
🖼️ Pixelsprite ai	Create good images for game assets in pixels every images use game and created transformation for treding images and auto background transparent	@ratherlive3-png
🖼️ ZEEK AI Girl Lab - BYOK Public Edition	ZEEK AI Girl Lab is a 100% client-side BYOK prompt forge for generating AI girl photos. Users bring their own Pollinations sk_... key (stored only in localStorage, zero server), expand prompts with QW	@hwoarangkang
💼 Jev AI - Chat with Jev	Jev AI - Chat with Jev is a lightweight browser-based interface for TypeSafe AI's Jev decision model through Pollinations. It allows users to define structured questions and application context, t	@alexsasha2750
🖼️ PIXOO64 Media Art	Pixoo64 Media Album Art is a native Home Assistant custom integration that transforms the Divoom Pixoo64 64×64 LED matrix into an intelligent media and visual display hub. Beyond traditional cover art	@idodov

Browse all apps →

🚀 Unified API

https://gen.pollinations.ai provides one API for text, images, audio, video, 3D, and embeddings.

What's Included

• 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, Claude, Gemini, Seedream, and more
• API keys: secret keys for model usage, app keys for tracking BYOP apps.
• CLI: npx @pollinations/cli for humans and AI agents (source)

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

🆕 Latest News

• ElevenLabs SFX v3 Nov 10Generate MP3 sound effects from text with elevenlabs/eleven-text-to-sound-v3. Set duration, looping, and prompt influence. Paid access is required.
• Scribe v3 batch transcription Nov 10Transcribe audio with elevenlabs/scribe-v3, including word timestamps and speaker labels in supported response formats. Paid access is required.
• Scribe v3 Live transcription Nov 10Use elevenlabs/scribe-v3-live for realtime transcription sessions with incremental and final transcripts. Paid access is required.
• Gemini Omni 1.2 Flash video Nov 9Generate paid videos with google/gemini-omni-1.2-flash from text or up to two reference images. It supports start and end frames, synchronized audio, and 3 to 15 second output from 360p through 4K.
• Longer Wan 3.0 videos Nov 9Choose any duration from 2 to 15 seconds for Wan 3.0 videos made from text, frames, or reference media. The default stays at 5 seconds.
• Claude Fable 5.2 added Nov 9Use paid-only anthropic/claude-fable-5.2 for text and image input, tools, and adaptive reasoning. It has a 1M-token context window and accepts up to 20 reference images.
• More details in model listings Nov 9Check /v1/models for video controls and durations, preset audio voices, and declared reference image and video limits. Fields appear only where a model defines them.
• Choose your model fallbacks Nov 6Set model to up to four comma-separated model IDs or aliases. If an upstream attempt fails in a retryable way, the API tries the next eligible model in order. Entries must share a category and support the requested endpoint.
• Compare sandbox templates Nov 6The searchable Sandboxes tab shows five E2B and Azure templates, with sizes, hourly prices, 720-hour monthly estimates, the 75% launch discount, and a polli sandbox create command for each.
• More sandbox pricing details Nov 6GET /alpha/e2b/pricing now includes each template's name, provider, size, and diskSizeMB alongside its existing fields.

More news on enter.pollinations.ai →

---

🌱 Introduction

pollinations.ai is an open-source generative AI platform based in Berlin, used by 500+ community projects. It provides APIs for text, image, video, audio, 3D, and embeddings generation. Our code and development discussions are public. Supporters help fund the project.

🚀 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
• 🖼️ Image Generation: Text-to-image and image editing
• 📝 Text Generation: Chat, reasoning, vision, function calling, structured outputs
• 🎬 Video Generation: Text-to-video and image-to-video
• 🎵 Audio: Text-to-speech and speech-to-text
• 🧊 3D Generation: Text-to-3D and image-to-3D
• 🎙️ Real-time API: OpenAI-compatible WebSocket for streaming conversations
• 🔢 Embeddings Creation: Semantic search, retrieval, similarity matching
• 🤖 Managed Agents: Turn a prompt, base model, and optional Pollinations tools into a reusable model
• 📦 Sandboxes: Cloud Linux computers for you or your agents, opened with SSH or VS Code
• 🌐 Sites: Free static hosting at <name>.pollinations.app
• 🎣 Easy-to-use Packages (Packages)

Guides

Guide	Purpose
Pollinations Pay (BYOP)	Let users pay with their own Pollen
Publish an Agent	Publish a hosted agent
Publish a Model	Connect your model endpoint
Sandboxes	Run code in a virtual machine
Sites	Host a static site at .pollinations.app
Coding Harnesses	Connect a coding assistant
MCP Servers	Give agents access to tools
CLI	Use Pollinations from a terminal

🤖 Managed Agents

Build a reusable text agent without hosting an agent server. Choose a system prompt and base model, optionally give it Pollinations tools, then call it through the same OpenAI-compatible API as any other model.

• Private or public: keep an agent owner-only or publish it after receiving community publisher access.
• Normal model API: call a registered agent by its owner/agent-name model ID.
• Dashboard, CLI, or API: manage agents in My Models, with polli agents, or through /account/agents.

See Publish an Agent for setup and billing behavior.

🛠️ Coding Harnesses

Run tools such as Bloom CLI, DeepSeek Harness, Hermes Agent, Mistral Vibe, OpenCode, Pi, Prime Agent, and tgpt on Pollinations models. polli harness edits the tool's own config so it calls Pollinations with a dedicated key, and restores it on off.

npx @pollinations/cli harness dsh on

See Coding Harnesses for supported harnesses and how to add one.

🧩 Community Models

Community members connect their own OpenAI-compatible text, image, image-editing, and speech-to-text endpoints to Pollinations.

• Host your own model: follow Publish a Model to test and register an upstream endpoint, then keep it private or publish it to the catalog.
• Automatic fallback routing: nominate up to three compatible backup models so generations keep moving when an upstream model goes down.
• Discover and monitor: browse community models via gen.pollinations.ai/v1/models and watch live health and community leaderboards at model-monitor.pollinations.ai.

For billing details when building apps on top, see Pollinations Pay.

🚀 Getting Started

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
• 🧊 3D
• 🔢 Embeddings

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

Image Generation

curl -H "Authorization: Bearer YOUR_API_KEY" 'https://gen.pollinations.ai/image/a%20beautiful%20sunset' -o image.jpg

Or visit pollinations.ai/play for an interactive experience.

Text Generation

curl 'https://gen.pollinations.ai/text/Hello%20world?key=YOUR_API_KEY'

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": "openai/tts-1", "input": "Hello from Pollinations!", "voice": "nova"}' \
  -o speech.mp3

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

Speech-to-text:

curl 'https://gen.pollinations.ai/v1/audio/transcriptions' \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F file=@audio.mp3 \
  -F model=openai/whisper-large-v3

Video Generation

curl 'https://gen.pollinations.ai/video/a%20sunset%20timelapse%20over%20the%20ocean?key=YOUR_API_KEY' -o video.mp4

Use duration to set video length, aspectRatio for orientation, and image[0]/image[1] to pass start/end reference frames. See available video models and capabilities at gen.pollinations.ai/video/models.

3D Generation

curl 'https://gen.pollinations.ai/3d/a%20low-poly%20treasure%20chest?model=microsoft/trellis-2&resolution=low&key=YOUR_API_KEY&image=IMAGE_URL' -o model.glb

Pass reference image URL(s) via the image parameter for image-to-3D models (put image= last in the URL, or URL-encode it). See available 3D models at gen.pollinations.ai/3d/models.

Embeddings

curl 'https://gen.pollinations.ai/v1/embeddings' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{"model": "openai/text-embedding-3-small", "input": "Hello world!"}'

Pass a string or an array of up to 32 strings (text or multimodal content parts). See available embedding models at gen.pollinations.ai/embeddings/models.

Pollinations CLI

Generate text, images, audio, video, and more right from your terminal:

npx @pollinations/cli gen image "cyberpunk city at night" --model black-forest-labs/flux.1-schnell --output city.png
npx @pollinations/cli gen text "Explain quantum tunneling in one sentence"
npx @pollinations/cli gen audio "Hello world" --voice nova --output speech.mp3
npx @pollinations/cli gen video "a waterfall in slow motion" --duration 5 --output clip.mp4
npx @pollinations/cli gen transcribe speech.mp3

Install globally and use the shorter polli command: npm install -g @pollinations/cli. Run polli models to list models, polli auth login to authenticate, and polli docs for the full API reference in your terminal.

Real-time API

Stream AI responses over an OpenAI-compatible WebSocket:

wss://gen.pollinations.ai/v1/realtime?model=openai/gpt-realtime-2.1&key=sk_YOUR_API_KEY

Browser clients pass a user-authorized key from Pollinations Pay as a query parameter (?key=); server clients can use the Authorization: Bearer header instead.

MCP Servers

Connect Streamable HTTP clients to the hosted Pollinations MCP server:

https://gen.pollinations.ai/mcp/pollinations

Send your Pollinations API key as an Authorization: Bearer header. See the MCP Servers documentation for the full hosted catalog.

🔐 Authentication

Get your API key at enter.pollinations.ai

Key Types

Key	Prefix	Use Case	Rate Limits	Status
App Key	pk_	Identifies your app in Pollinations Connect	Can't authenticate requests	Stable
Secret	sk_	Server-side only	No rate limits	Stable

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

💡 Building an app? Use Pollinations Pay: users pay for their own usage, you pay $0

Model Restrictions

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

• Allow all models: key works with any available model
• Restrict to categories: e.g. only image, or image and text. A key allows every model in its categories, including models added later
• Restrict to specific models: through the API or polli keys update <id> --models black-forest-labs/flux.1-schnell tongyi-mai/z-image-turbo; a model ID allows only that model

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

Visit the playground to generate content in your browser.

Here are some examples of what you can generate:

🛠️ Integration

SDK

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

OpenAI SDK Compatibility

The API is OpenAI-compatible. Set the base URL in an official OpenAI SDK to https://gen.pollinations.ai/v1.

Node.js:

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gen.pollinations.ai/v1",
  apiKey: "YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-5.4-nano",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Python:

from openai import OpenAI

client = OpenAI(base_url="https://gen.pollinations.ai/v1", api_key="YOUR_API_KEY")

response = client.chat.completions.create(
    model="openai/gpt-5.4-nano",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Other OpenAI SDKs work too: Go, Java, .NET, Rust (async-openai, community), plus compatible frameworks like Vercel AI SDK.

Vercel AI SDK:

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { generateText } from "ai";

const pollinations = createOpenAICompatible({
  name: "pollinations",
  baseURL: "https://gen.pollinations.ai/v1",
  apiKey: "YOUR_API_KEY",
});

const { text } = await generateText({
  model: pollinations.chatModel("openai/gpt-5.4-nano"),
  prompt: "Hello!",
});
console.log(text);

Streaming, image, and embedding examples: API docs → Vercel AI SDK.

Architecture

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

graph LR
    subgraph CLIENTS["Clients / Apps"]
        Q[Bots - Discord, Telegram, WhatsApp]
        N[30+ Mobile and Web Apps]
        A[pollinations.ai Web Frontend]
        R[AI Agents - Qwen, Sillytavern, ...]
        AI[AI Assistants - Claude]
        MCP[MCP Server]
    end

    AI --> MCP
    Q --> GEN
    N --> GEN
    A --> GEN
    R --> GEN
    MCP --> GEN

    GEN["gen.pollinations.ai: Edge Router + Generation Worker"]:::cfWorker -->|auth and billing| ENTER["enter.pollinations.ai: Auth Gateway + Billing"]:::cfWorker

    GEN --> IMG["Image: gen Worker dispatch to providers / GPU backends"]:::cfWorkerLight
    IMG --> D["Flux, Z-Image, Seedream, ...: GPU VMs"]:::gpuNode

    GEN --> TXT["Text: Portkey multi-provider"]:::provider
    GEN --> VID["Video: Wan / Veo / Seedance"]:::provider
    GEN --> AUD["Audio: ElevenLabs / OVH (Whisper)"]:::provider

    style CLIENTS fill:none,stroke:#888,stroke-width:2px,stroke-dasharray: 5 5

    linkStyle default stroke-width:3px,stroke:#00E5FF

    classDef cfWorker fill:#E65100,color:#fff,stroke:#FFB300,stroke-width:2px,font-weight:bold
    classDef cfWorkerLight fill:#BF360C,color:#fff,stroke:#FFB300,stroke-width:1px
    classDef gpuNode fill:#064E3B,stroke:#34D399,color:#ECFDF5,stroke-width:2px
    classDef provider fill:#1E3A8A,stroke:#60A5FA,color:#EFF6FF,stroke-width:1px

🔮 Future Developments

We're exploring:

• Digital Twins: Creating interactive AI-driven avatars
• Music Video Generation: Combining AI-generated visuals with music
• Real-time AI-driven Visual Experiences: Projects like our Dreamachine