Search the live web and fetch clean content from source pages.
io.github.pollinations/exa MCP Server
The io.github.pollinations/exa MCP server performs live web search and fetches clean content from source pages. It is described as a tool for retrieving processed web content suitable for downstream use, based on its capability to search the web and return cleaned results.
๐ ๏ธ Key Features
Live web search
Fetches clean content from source pages
๐ Use Cases
Finding relevant information on the live web
Pulling and using cleaned content from web sources
โก Developer Benefits
Centralizes web search plus content retrieval into one server capability
Provides โclean contentโ output from source pages
โ ๏ธ Limitations
Limited to the scope of live web search and clean content fetching, as described
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.
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.
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.
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.
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
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
Pixoo64 Media Album Art is a native Home Assistant custom integration that transforms the Divoom Pixoo64 64ร64 LED matrix into an intelligent media and visual display hub. Beyond traditional cover art
Describe a fighter in one line: the AI designs it (portrait, stats, moves, a weakness) and commentates the brawl. Ladder, daily boss, voice and share links. Players pay with their own Pollen.
Explorable postcard worlds. You type a scene, and the first postcard is painted from it. Then you click the doors, paths and windows in the picture to step into the next view โ one painted pos
Gemini Omni 1.2 Flash videoNov 9 Generate 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 videosNov 9 Choose 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 addedNov 9 Use 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 listingsNov 9 Check /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 fallbacksNov 6 Set 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 templatesNov 6 The 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 detailsNov 6 GET /alpha/e2b/pricing now includes each template's name, provider, size, and diskSizeMB alongside its existing fields.
GPT Image 2.6 FlareNov 5 Generate and edit images with openai/gpt-image-2.6-flare, using up to 16 reference images, transparency, and 4K output. It requires purchased Pollen.
GPT Image 2.6 SunburstNov 5 Generate and edit images with openai/gpt-image-2.6-sunburst, using up to 16 reference images, transparency, and 4K output. It requires purchased Pollen.
Invite friends for PollenNov 5 The new Invite friends quest awards 2 Quest Pollen for each qualifying referral whose purchases total more than 2 Pollen. Connect GitHub to copy your invite link from the Quests page.
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.
๐ Key Features
๐ 100% Open Source: code, decisions, roadmap all public
๐ค Community-Built: 500+ projects already using our APIs
๐ฑ Pollen Quests: earn Pollen by completing Quests
๐ผ๏ธ Image Generation: Text-to-image and image editing
๐ Text Generation: Chat, reasoning, vision, function calling, structured outputs
๐ฌ Video Generation: Text-to-video and image-to-video
๐ต Audio: Text-to-speech and speech-to-text
๐ง 3D Generation: Text-to-3D and image-to-3D
๐๏ธ Real-time API: OpenAI-compatible WebSocket for streaming conversations
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.
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.
bash
npx @pollinations/cli harness dsh on
See Coding Harnesses for supported harnesses and how to add one.
๐งฉ 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.
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.
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.
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:
bash
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:
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:
text
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.
โ ๏ธ Never expose sk_ keys in client-side code, git repos, or public URLs
๐ก 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
%%{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
๐ฎ 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
๐ Our Vision
We want AI tools to be:
Open & Accessible: Earn Pollen by contributing, without a credit card
Transparent & Ethical: Inspect our code and discuss how the platform works
Community-Driven: Build tools with other developers, creators, and AI enthusiasts
Interconnected: Combine models and services through shared APIs
Evolving: Add new capabilities while keeping the platform open and accessible
๐ค Community and Development
You can contribute to pollinations.ai in several ways:
Coding Assistant: Create a GitHub issue describing a feature for the Polli assistant to work on. You can propose a change without writing code.
Project Submissions: Have you built something with pollinations.ai? Use our app submission template to share it with the community and get it featured in our README.
Feature Requests & Bug Reports: Have an idea or found a bug? Open an issue and let us know. Our team and the Polli assistant will review it.