unbiased ai

Cherry Studio, with Pareto writing the answers

Cherry Studio keeps your providers, assistants and knowledge bases in one desktop app, and its custom provider dialog takes any OpenAI or Anthropic compatible address. Add Unbiased there and Pareto joins the model list. It selects frontier and open models for each request and blends their outputs into one answer, written from the passages your knowledge base finds, with the sources one click away.

Choose Personal · $10/month See the setup →

Settings from Cherry Studio’s docs50M tokens a week

An illustration of Cherry Studio on Pareto. Not a screenshot.

Set it up as a custom provider

Cherry Studio adds providers from Settings > Model Provider (the docs call this tab Model Services). Unbiased goes in as a custom provider with an OpenAI endpoint. You can add an Anthropic endpoint at the same address too; Unbiased answers both formats.

  1. Get an Unbiased API key

    Choose a plan, then create a key in the Unbiased platform. New accounts are reviewed and approved by a person before the key works.

  2. Add a custom provider

    Open Settings (the gear), go to Model Provider and click + Add Provider below the list. In Add Custom Provider, name it Unbiased, paste your key into API Key and set the OpenAI endpoint to https://api.unbiased.ai. Enter the root only: Cherry Studio adds /v1/chat/completions itself. Optionally, set the Anthropic endpoint to the same root. Click Add.

  3. Add pareto by hand

    Open the new provider and click + (Add model manually). Type pareto as the Model ID. Under Model Capabilities, make sure Tool is on: Cherry Studio only lets a tool-capable model search a knowledge base.

  4. Check, enable and chat

    Click Check next to the API key, turn on the switch at the top right of the provider page if it is off, then choose Unbiased > pareto in the model selector at the top of a chat.

Settings follow Cherry Studio’s own documentation: Cherry Studio docs: Custom providers.

Add Custom Provider
Provider Name:  Unbiased
API Key:        your-unbiased-api-key
OpenAI:         https://api.unbiased.ai
# Optional:
Anthropic:      https://api.unbiased.ai
Models > + (Add model manually)
Model ID:       pareto
# Model Capabilities: turn on Tool

The preview line under the address should read https://api.unbiased.ai/v1/chat/completions. If it shows /v1/v1, remove the /v1 you typed. Pareto writes the answers; it does not supply embeddings, so your knowledge bases keep the retrieval you set up for them. These steps were checked against Cherry Studio 2.1.7.

Cherry Studio stays. The model changes.

You add one provider and one model. Your assistants, topics and knowledge bases stay where you left them.

One model string, several models behind it

Pareto is Unbiased’s blended AI model. On each request it selects frontier and open models and blends their outputs into one answer, so Cherry Studio talks to one model string, pareto, and never has to pick.

“When the frontier improves, Pareto improves; when frontier prices fall, you should benefit.” From the pricing page.

How a Pareto answer gets made →
An illustration, not a wiring diagram. The blend includes frontier and open models, and its composition can change.

What an agent task costs on Pareto

A chat reply takes a model call or two. Cherry Studio’s Agent working through a task can make many, so the price of a finished task matters more than the price of a token. The model card publishes both for Pareto on two public agent benchmarks.

Terminal-Bench 4.0Tasks an agent completes in a terminal
$0.48/task
50.8% solved
DeepSWE v1.1Changes an agent makes in a real codebase
$0.24/task
69.9% solved

Pareto 26.10, preliminary October 1, 2026 runs that may change; denominators and the cost method still require confirmation. Cost is the reported mean USD per task at API rates, not an estimate for your workload. Model card and method.

Cherry Studio is open source. The model is the bill.

Pareto is the part you pay for: pick a monthly allowance, or pay per token on Team. The same key works in any other tool you point at Pareto.

Personal

$10/month

  • 50M tokens a week
  • 20 requests per minute
  • For one person
Choose Personal

Personal Max

$100/month

  • 600M tokens a week
  • 60 requests per minute
  • For one person
Choose Personal Max

Team

Pay as you go

  • Prepaid credits at published rates
  • 300 requests per minute
  • No weekly token cap
Get started with Team

Subscriptions are for one person and are not unlimited. New API accounts are reviewed by a person before access turns on, and commercial or production use needs a separate written agreement. Rates and limits are on Pricing.

Cherry Studio on Pareto, questions answered

Which endpoint do I fill in, OpenAI or Anthropic?

Fill in OpenAI with https://api.unbiased.ai; that is what ordinary chats use. The Anthropic endpoint is optional; if you add it, use the same address. Unbiased answers both formats with the model pareto. Older guides show a Provider Type dropdown; current versions show Endpoint settings in the Add Custom Provider dialog instead.

Why add the model by hand instead of using Sync models?

Unbiased’s published API does not offer a model list, so do not count on Sync models to find Pareto. Click +, type pareto and you are done. It is the only model name you need.

Why is the Knowledge Base button greyed out?

If it says Select a tool-capable model, Cherry Studio does not know that pareto can call tools. Edit the model under your Unbiased provider and turn on Tool in Model Capabilities. The button is also disabled while a file is attached to the message.

Does Pareto read my whole PDF?

No. Cherry Studio searches the knowledge base, by keyword (BM25) or with an embedding model you choose, and sends Pareto the passages it finds. Pareto writes the answer from those passages, and the citations show which ones it used. Scanned PDFs need Cherry Studio’s document processing or OCR first, or there is no text to find. If an answer misses, run the same question in the knowledge base’s retrieval test to see what was found.

Has this been tested inside Cherry Studio?

Not yet. These settings follow Cherry Studio’s documentation and its settings screens, and the Unbiased endpoints they call answer Chat Completions and Messages requests for pareto. Format compatibility is not a promise that every Cherry Studio feature works, so tell us if one doesn’t. If you would rather skip the setup and just chat, see the ChatGPT alternative page.

Is Pareto made by the Cherry Studio team?

No. Pareto is Unbiased’s model. Cherry Studio is made by CherryHQ, and Unbiased is not affiliated with or endorsed by them. You keep Cherry Studio and point it at the Unbiased API.

What happens when I hit the weekly allowance?

Requests over your plan’s limits return an HTTP 429 error. Personal includes 50M tokens a week and 20 requests per minute. Personal Max raises that to 600M a week and 60 requests per minute for $100/month. Team uses prepaid pay-as-you-go credits with no weekly token cap.

Do I choose between models?

No. You send every request to one model string, pareto. Pareto selects frontier and open models for each request and blends their outputs into one answer.

Is my code kept?

Personal and Personal Max are not our zero data retention tier: prompts and responses may be kept up to 30 days, as section 5(c) of the Terms explains. For work that must not be kept, ask about the Zero Data Retention API on the Private AI page.

Pareto works in other tools too

The same key and the same model string go into each of these. See them all.

Product names belong to their owners. Except where a guide says otherwise, Unbiased is not affiliated with or endorsed by the makers of the tools on this page.

Give Cherry Studio the policy nobody reads to the end

One custom provider, one key and the knowledge bases you already built. Pareto starts at $10 a month for 50M tokens a week.

Choose Personal · $10/month See the setup →