unbiased ai

Pareto, one entry in Continue’s config.yaml

Continue was built so you could choose the model behind it. Add Pareto to config.yaml with the openai provider and Unbiased’s base URL, and the extensions and cn read it. Pareto selects frontier and open models for each request and blends their outputs into one answer.

Choose Personal · $10/month See the setup →

Tested live with Continue CLI 1.5.4750M tokens a week

An illustration of Continue on Pareto, recreated from a real run of the Continue CLI. Not a screenshot.

Set it up in one config file

Continue reads its models from ~/.continue/config.yaml. Add Pareto as a model that uses the openai provider with Unbiased’s base URL. The IDE extensions and the cn CLI read the same file.

  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 Pareto to config.yaml

    Under models, add an entry with provider: openai, model: pareto and apiBase: https://api.unbiased.ai/v1. Keep /v1 on the base URL.

  3. Type the model name yourself

    Unbiased does not list models at /v1/models, so Continue cannot list it for you. Write pareto by hand, exactly as shown.

  4. Turn on tool use

    Add capabilities: [tool_use]. Continue’s reference says tool use is required for Agent mode, and Continue cannot detect it for a model name it does not know.

  5. Pick Pareto and give it a task

    In VS Code or JetBrains, choose Pareto in the model dropdown in the chat input. In a terminal, run cn with --config pointing at the file.

Tested on October 20, 2026Continue CLI 1.5.47 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.
~/.continue/config.yaml
name: Unbiased
version: 0.0.1
schema: v1
models:
  - name: Pareto
    provider: openai
    model: pareto
    apiBase: https://api.unbiased.ai/v1
    apiKey: your-unbiased-api-key
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
Terminal (Continue CLI)
npm i -g @continuedev/cli
# interactive session
cn --config ~/.continue/config.yaml
# one task, all tools allowed
cn --config ~/.continue/config.yaml --auto -p "test_chunk.py fails. Fix the bug in chunk.py, then run python3 test_chunk.py to confirm."

Without --config, cn reads ~/.continue/config.yaml if it exists and falls back to Continue’s default agent if it does not. Passing --config makes sure it loads the file with Pareto in it.

Continue stays. The model entry changes.

Pareto is one more model in the file. Everything else in Continue keeps working the way you set it up.

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 Continue 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 Pareto by the month

One API key works across Continue 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.

Continue on Pareto, questions answered

Which provider do I pick for Pareto in Continue?

Use provider: openai with apiBase: https://api.unbiased.ai/v1. Unbiased speaks the OpenAI Chat Completions format, and in our run Continue streamed its requests to /v1/chat/completions. Format compatibility is not a promise that every Continue feature works, so tell us if one doesn’t.

Did you test the VS Code and JetBrains extensions?

We ran the Continue CLI, cn 1.5.47, against Pareto on October 20, 2026: it read a failing Python test, fixed the off-by-one in chunk.py and reran the test to ok. The extensions read the same config.yaml, but that run used the CLI.

Why add capabilities: tool_use?

Continue detects tool support for most known models, but pareto is a name it has not seen. Its config reference says tool_use is required for Agent mode. With the flag set, cn read, edited and ran files in our test.

Can I raise the context limit?

Yes. In our run the Continue CLI used its default 200,000-token limit, since the entry sets none. Pareto accepts about 1M tokens of context, so you can set defaultCompletionOptions.contextLength on the model entry if you want more. Leaving it alone works too.

Can I keep my other models next to Pareto?

Yes. Pareto is one entry in the models list. Switch between it and your other models in the dropdown, or remove the entry to stop using it.

Is Pareto made by the Continue team?

No. Pareto is Unbiased’s model. Continue is made by Continue (Continue Dev, Inc.), and Unbiased is not affiliated with or endorsed by them. You keep Continue 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.

Continue, but on Pareto

Fifteen lines of YAML and one key. Pareto starts at $10 a month for 50M tokens a week.

Choose Personal · $10/month See the setup →