Skip to content

ModelPiper

A browser-based UI for chatting with models and tools, processing images, and creating in Studio. Works with cloud APIs, local models, or both.

Getting Started

ModelPiper connects to AI providers to run inference. You can get started in minutes with any of these options:

Easiest

ToolPiper

macOS companion app that bundles local inference (llama.cpp, speech-to-text, text-to-speech, image upscaling), proxies cloud APIs securely, and manages model downloads.

1Install ToolPiper from modelpiper.com/download
2Launch it — ModelPiper automatically detects the connection
3Automatically get push-button templates and local model downloads
Cloud

OpenRouter

Access 300+ models (GPT-4o, Claude, Gemini, Llama, Mistral, and more) through a single API key, kept in your Mac's Keychain by ToolPiper.

1Create a free account at openrouter.ai and generate an API key
2In ToolPiper, open Models › Providers and click New provider
3Select OpenRouter, paste your API key, and pick a model
4Save the configuration — you're ready to use Chat
Local

Ollama

Run open-source models entirely on your machine. Free, private, no API key needed.

1Install Ollama from ollama.com and pull a model (e.g. ollama pull llama3.2)
2Start Ollama with CORS enabled: OLLAMA_ORIGINS=* ollama serve
3In ModelPiper, add an Ollama provider — it auto-detects your models

Connecting AI Providers

Providers are managed in ToolPiper's Models › Providers, which Providers under the app's connection indicator opens. Each provider can be used across Chat, Studio, and other features.

Cloud Providers

Cloud providers such as OpenRouter, OpenAI, Anthropic and Google Gemini run through the ToolPiper companion app, which adds your key from the Keychain and sends each request from your Mac.

Local Providers

Ollama and LM Studio run on your machine and connect over localhost. Models stay on your hardware, and your prompts stay on your machine.

Custom Endpoints

Any OpenAI-compatible API can be added as a custom provider. Set the host, port, path, and auth pattern to match your server.

Features

Chat

Multi-model chat interface. Streaming responses, system prompts, conversation history, and provider switching mid-conversation.

Image

CoreML-powered image upscaling with side-by-side comparison. Requires ToolPiper for the upscaling backend.

Studio $29/mo

API Keys & Privacy

Where are my keys stored?

ToolPiper stores API keys in the macOS Keychain on your Mac. The web app never reads a key back; ToolPiper adds it to requests for the provider it belongs to and never sends it to ModelPiper.

What data is sent externally?

Your prompts and parameters go only to the model you choose: a local model on your Mac, or a cloud provider that ToolPiper calls from your Mac. They never pass through ModelPiper servers. ToolPiper does contact our servers for update checks, a license check when you're signed in, a daily activity count and optional usage counts; none of these include your content, and you can turn the last two off in Settings. modelpiper.com uses PostHog website analytics, linked to your account email after you sign in.

Companion Apps

ModelPiper works standalone, but companion apps unlock additional capabilities:

ToolPiper

Local AI gateway — inference engines, cloud proxy, model management, speech & audio

VisionPiper

Screen capture, recording, GIF conversion, and live streaming

AudioPiper

Multi-source audio mixer — mic, system audio, and per-app capture

MediaPiper

Browser extension — image & video hover preview, intelligent discovery, on-device AI upscaling