unbiased ai

Cline, with Pareto as the API Provider

Cline can ask before it edits a file or runs a command, plan before it acts, and use a model you bring. Pick OpenAI Compatible as the API Provider, give it the Unbiased base URL, your key and the model ID pareto, and every task goes to Pareto. On each request Pareto selects frontier and open models and blends their outputs into one answer.

Choose Personal · $10/month See the setup →

Tested live with the Cline CLI 3.0.7350M tokens a week

An illustration of Cline in VS Code on Pareto, based on a real run in the Cline CLI. Not a screenshot.

Point Cline at Pareto

Cline’s OpenAI Compatible provider takes a base URL, a key and a model ID. Set it once in the VS Code extension, or once with cline auth in the terminal.

  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. Open Cline’s settings

    In VS Code, open the Cline panel and click the gear icon. Set API Provider to OpenAI Compatible.

  3. Enter the base URL and key

    Set Base URL to https://api.unbiased.ai/v1, with the /v1, and paste your key into API Key.

  4. Type the model ID by hand

    Enter pareto as the model. Unbiased does not publish a model list, so there is nothing for Cline to fetch; typing it is the whole step. The Model Configuration fields are optional.

  5. Or set up the Cline CLI

    Install it with npm, run cline auth once with the provider openai-compatible, then start tasks with -P openai-compatible -m pareto. This is the setup we ran live.

Tested on October 20, 2026Cline CLI 3.0.73 on Pareto (pareto). It found the off-by-one in a failing Python test, edited the file and reran the test to green. Run record.
Cline extension settings
API Provider: OpenAI Compatible
Base URL:     https://api.unbiased.ai/v1
API Key:      your-unbiased-api-key
Model:        pareto
Cline CLI
npm i -g cline
cline auth -p openai-compatible -k your-unbiased-api-key -m pareto -b https://api.unbiased.ai/v1
# then, in a project (-y runs unattended and exits when the task is done)
cline -y -P openai-compatible -m pareto "test_chunk.py fails. Fix the bug in chunk.py, then run python3 test_chunk.py to confirm."

cline auth saves the key in plain text in ~/.cline/data/settings/providers.json. Set CLINE_DIR to keep it somewhere else. Run unattended -y tasks on a clean branch. The CLI approves tool calls automatically unless you pass --auto-approve false. Flags and paths: Cline CLI reference.

Cline stays. The model changes.

The provider and the model ID change. Your approval settings, rules and MCP servers stay as you set 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 Cline 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

Agents make many model calls per task, 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.

Pay for Cline by the month

One API key works across Cline and any other tool you point at Pareto. Pick a monthly allowance, or pay per token on Team.

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.

Cline on Pareto, questions answered

Which API Provider should I pick in Cline?

OpenAI Compatible, with the base URL https://api.unbiased.ai/v1. The provider named OpenAI is for OpenAI’s own API. In the CLI the same choice is openai-compatible; OpenAI’s own API is openai-native.

Does Cline really work on Pareto?

We ran the Cline CLI 3.0.73 against Pareto on October 20, 2026. It read the failing test, fixed the off-by-one in chunk.py and ran the test to ok. The VS Code extension uses the same provider settings. Format compatibility is not a promise that every feature works, so tell us if one doesn’t.

Why isn’t pareto in the model dropdown?

Unbiased does not publish a model list, so there is nothing for the dropdown to show. Type pareto into the model field and Cline sends it as is.

Do I need a Cline account or Cline credits?

Not for this. With OpenAI Compatible selected, Cline sends requests to Unbiased with your Unbiased key, and your Unbiased plan pays for them. To switch back, choose another API Provider in the settings, or pass a different -P in the CLI.

Is Pareto made by the Cline team?

No. Pareto is Unbiased’s model. Cline is made by Cline Bot Inc., and Unbiased is not affiliated with or endorsed by them. You keep Cline 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.

Switch Cline to Act and let it fix the test

One provider, one key, one model ID, and the approval settings you already chose. Pareto starts at $10 a month for 50M tokens a week.

Choose Personal · $10/month See the setup →