ModelPiper pricing

Everything Ollama does, free — model downloads, the native llama.cpp engine, multi-model, the local OpenAI-compatible API. No account, no caps. Paid tiers cover what no model runner does: dictation, speech, vision, system control, and developer tools.

Explore plans

Free for everyone. Pro for the full toolkit. Studio for creators, Max for developers. Team for your whole office on one Mac.

Free

Everything Ollama does, free. No account, no caps.

Native llama.cpp engine — run any GGUF model
Unlimited model downloads, multi-model switching
Local OpenAI-compatible API + embeddings
MCP server with 359 free tools
All speech: transcription, text-to-speech, voice cloning, dictation
Chat with bundled model
Apple Intelligence on the Neural Engine
Full browser automation, vision, and system control
Visual pipeline builder
Free companion apps (VisionPiper, AudioPiper, MediaPiper)

Pro

What no model runner does, at any price.

$10/mo

Everything in Free
Local RAG over your files
Web scraping and YouTube transcripts
Cloud API proxy (bring your own keys)

Studio

For content creators and marketers.

$29/mo

Everything in Pro
Image upscaling (ANE-native)
Video upscaling (60fps real-time)
Video editing pipeline
Pose detection (60fps streaming)
Outreach toolkit (queue, posting, Firehose)

Max

For developers and QA engineers.

$49/mo

Everything in Studio
Code (agentic AI code editor)
PiperTest (self-healing browser tests)
API discovery toolkit
Priority support

For teams

Team

One Mac runs your AI. Your whole team uses it — governed, audited, private.

$99/mo per deployment

Everything in Max, on the deployment
Unlimited named member tokens — no per-seat pricing
Per-user attributed audit trail with pull export
Remote tool governance from modelpiper.com
Clients on any OS via piper-bridge
Priced per deployment — add Macs as you grow

Add-ons

Optional. Available on any plan, Free included.

Coming soon

Devices add-on

PiperMesh

Your Mac runs the AI. Your phone, watch, and PC just talk to it.

+$7/mo

iPhone, iPad, and Apple Watch apps
Up to 4 paired devices
End-to-end encrypted
One primary Mac hosts, everything else connects
Works on any tier, Free included

Learn more

Coming soon

Devices add-on

PiperMesh Family

The whole household on one Mac. Twenty devices, one subscription.

+$19.99/mo

iPhone, iPad, and Apple Watch apps
Up to 20 paired devices
End-to-end encrypted
One primary Mac hosts, everything else connects
Works on any tier, Free included

Learn more

Compare plans

Everything that ships with each tier.

Feature	Free	Pro	Studio	Max
Inference & Models
Native llama.cpp engine (Metal GPU)
Model downloads (GGUF / MLX)	Unlimited	Unlimited	Unlimited	Unlimited
Multi-model switching
Local OpenAI-compatible API
Local embeddings
Local chat (bundled model)
Cloud API proxy (BYO keys)
Apple Intelligence
Voice
Transcription (STT)
Text-to-speech (TTS)
Push-to-talk dictation
Push-to-talk AI commands
Pipeline Builder
Visual pipeline builder
Local RAG over files
Tools & Automation
MCP server (local HTTP)
MCP tools	over 420 tools	over 420 tools	over 420 tools	over 420 tools
Browser automation
Web scraping (page + YouTube transcript)
System actions	26 domains	26 domains	26 domains	26 domains
Clipboard integration
Companion Apps
VisionPiper (screen capture & streaming)
AudioPiper (per-app audio capture)
MediaPiper (browser extension)
Content & Media
Image upscaling (ANE-native)
Video upscaling (60fps real-time)
Video editing pipeline
Pose detection (60fps streaming)
Outreach toolkit (queue, posting)
Developer Tools
Code (agentic AI code editor)
PiperTest (self-healing browser tests)
API discovery toolkit
Priority support

The free engine is llama.cpp, embedded directly — currently llama-server b10068. The version ships in the app's About panel and updates with every upstream bump.