Your session has been flagged for unusual activity.
Please confirm you're human to continue.
OpenRouter desktop client · Your own API key
One OpenRouter key. Your choice of models. Bring them into a desktop app for Mac and Windows, with conversations stored on your computer.
24-hour trial · $250 one-time license
Cloud API usage billed separately. Local models use your hardware.
MultipleChat On your computer•••• •••• •••• ••••Your chat history stays in the desktop app.
Illustrated setup. Cloud requests leave your computer.
Take a closer look
A general illustrated walkthrough of MultipleChat's provider setup. Follow the specific connection details below for OpenRouter.
Your computer. Your own API keys. · Illustrated walkthrough; screens are simplified.
OpenRouter connection guide
Connect OpenRouter once, then choose among the chat models available to your account. MultipleChat groups its OpenRouter model list by organization, making it easier to find the family you want.
| Choose this provider | OpenRouter |
|---|---|
| Use this key | OpenRouter API key |
| Choose a model | A chat model from the OpenRouter list |
| API usage billed through | OpenRouter |
| Where requests go | Your computer → OpenRouter → model host |
Use a default model for everyday chats and a different one for another workspace. Qwen and Kimi are two families you can look for in the OpenRouter list. Availability, pricing and supported features vary by model.
Your OpenRouter account handles API credit and usage. The MultipleChat license does not include OpenRouter credit. A key from an individual model provider is not the OpenRouter API key requested by this connection.
This guide keeps your chat history on your computer, while the configured API processes requests in the cloud. Prompts and relevant document passages go through the connection shown above. To run inference on your own hardware, use a local model.
Check your internet connection, reopen the provider settings and let the model list load. Confirm that your installed app is up to date.
Check your OpenRouter credit, key limits and the selected model's availability. Try a short text-only message before adding files or tools.
The OpenRouter settings include an advanced Stream Timeout control. A slow model or host may need more time between response chunks; also check OpenRouter's status.
Provider references: OpenRouter documentation · Qwen model catalog · Kimi model catalog. Reviewed 24 October 2026. Model availability depends on your account and installed app release.
MultipleChat is an independent desktop app, not an official OpenRouter product. Provider and model names belong to their respective owners.
Getting started
Have your OpenRouter API key and any required API credit ready before starting the 24-hour app trial.
Have your API key or local model ready before clicking Start trial. Your 24 hours begin at that point. A consumer AI subscription does not automatically include API credit.
Download for Mac or Windows and check the platform requirements. This is an independent desktop app with a separate license.
Open Settings → AI Providers → LLM, select OpenRouter, and enter your OpenRouter API key in the app.
In Chat Model Selection, choose a chat model under its organization. Save it as your default, or set a different model for a workspace. Start with a plain text conversation.
Save the provider settings, create a workspace and send a short message. Check usage in OpenRouter after testing. Keep your API key private.
Your desktop app license
Try MultipleChat AI Desktop on your own computer before buying. Your license key arrives by email.
No recurring app subscription. Cloud model usage is billed separately by your provider.
Before you download
No. MultipleChat is an independent desktop client that connects to OpenRouter using your API key. It is not published by or affiliated with OpenRouter.
No. Your chat history is stored locally, but this connection sends requests to OpenRouter and the selected model host. For inference on your computer, use a local model runner instead.
You can choose available Qwen and Kimi chat models through the OpenRouter connection using your OpenRouter API key. Each model has its own pricing, capabilities and availability.
Create an API key with a supported provider and add it in Settings → AI Providers → LLM. The app connects directly to that provider using your key. API usage is billed to your provider account separately from the app license.
Your chat history, documents, local document index and API keys are stored on your computer. When you choose a cloud model, your prompt and any relevant document passages are sent to that provider under its terms. No MultipleChat server sits between your app and the model provider.
Yes. Connect a local model through Ollama or LM Studio. Local chat and document indexing can run on your computer without cloud API usage charges. Model performance depends on your hardware. A licensed copy needs an online check-in at least every 14 days; web search and cloud models also need an internet connection.
Try the app for 24 hours. The trial starts when you click Start trial, so prepare your API key or local model first. A license costs $250 as a one-time purchase. Cloud API usage is charged separately by your provider. Local models use your own hardware without per-token provider fees.
No. MultipleChat AI Desktop is a separate, single-user product using your own API keys or local models. The web subscription and web-only features, including the Studios and AI Collaboration, are separate.
Your license key is emailed to the address you use at checkout. Enter it under Settings → License. If the email does not arrive, check your spam folder or contact [email protected].
Need help connecting your AI? Read the setup guide or contact support.
Your providers. Your desktop.
Connect OpenRouter or a direct provider account. Each guide shows which key to use, how to choose a model, and where your requests go.