unbiased ai

Your n8n AI Agent, running on Pareto

Your workflows already know where the emails come from and where the answers go. Leave every trigger, branch and node where it is, and change the one thing in the middle: the model. Give n8n’s OpenAI credential a new Base URL and the model ID pareto, and each request goes to Pareto, which consults a blend of frontier and open models and sends back one answer.

Choose Personal · $10/month See the setup →

Settings from n8n’s docs50M tokens a week

An illustration of n8n on Pareto. Not a screenshot.

Set it up in one credential and one field

n8n talks to OpenAI through a credential with a Base URL field. Point that field at Unbiased, then tell the OpenAI Chat Model node to use the model ID pareto. Any node that takes a Chat Model, the AI Agent included, can use it.

  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. Create an OpenAI credential

    In n8n, go to Credentials, create a new OpenAI credential, paste your key into API Key and set Base URL to https://api.unbiased.ai/v1. Keep the /v1: n8n uses the full URL as the API base.

  3. Choose the model by ID

    Open the OpenAI Chat Model node attached to your AI Agent, select the new credential under Credential to connect with, switch Model from From List to ID and type pareto.

  4. Turn off Use Responses API

    Newer versions of the node turn on Use Responses API by default. Turn it off to send standard Chat Completions requests. That also hides Built-in Tools, which OpenAI hosts.

  5. Open chat and send a message

    Click Open chat on the canvas, ask something and watch the execution. Your workflow is unchanged apart from the model it calls.

Settings follow n8n’s own documentation: n8n docs: OpenAI Chat Model node.

Credential: OpenAI
API Key: your-unbiased-api-key
Organization ID (optional): leave blank
Base URL: https://api.unbiased.ai/v1
Node: OpenAI Chat Model
Credential to connect with:
  the OpenAI credential above
Model: ID
  pareto
Use Responses API: off
# The Base URL lives on the credential.

When you save the credential, n8n tests it by asking for a model list. Unbiased’s published docs don’t offer model listing, so a failed test does not by itself mean the key is wrong. Run the workflow to check.

The workflow stays. The model changes.

One credential gets a new address and one field gets a new name. Every other node carries on as before.

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 n8n 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

An AI Agent run can call the model several times before it answers, 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 n8n by the month

One API key works across n8n 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.

n8n on Pareto, questions answered

Why isn’t pareto in the model list?

In From List mode n8n fetches models from the API, and Unbiased’s published docs say model listing is not offered. Switch the Model field to ID and type pareto; n8n sends that name with each request.

Should I use the OpenAI node or a different chat model node?

Use the OpenAI Chat Model sub-node with an OpenAI credential. Its Base URL field is what lets n8n reach Unbiased, and Unbiased accepts the OpenAI Chat Completions format at https://api.unbiased.ai/v1.

Do tools and structured output work?

Pareto accepts tool definitions in the Chat Completions format, but we have not run n8n against it yet, and format compatibility is not a promise that every feature works. n8n’s own node notes that non-OpenAI models reached through a Base URL override might not support tools calling or JSON response format. The Built-in Tools (Web Search, File Search, Code Interpreter) are run by OpenAI and should not be expected to work.

Can I run this in a production workflow?

Personal and Personal Max are for one person. Commercial or production use needs a separate written agreement, so talk to us before a workflow that serves customers depends on it.

Can I switch back to OpenAI?

Yes. Pick a different credential in the node, or set the Base URL back to https://api.openai.com/v1 with an OpenAI key, and choose an OpenAI model again.

Is Pareto made by the n8n team?

No. Pareto is Unbiased’s model. n8n is made by n8n GmbH, and Unbiased is not affiliated with or endorsed by them. You keep n8n 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.

Put Pareto in the Chat Model slot

One credential, one model ID and the same workflows. Pareto starts at $10 a month for 50M tokens a week.

Choose Personal · $10/month See the setup →