unbiased ai

AnythingLLM, answering with Pareto

AnythingLLM runs on your desktop or your own server and holds your workspaces, documents and agents. It also ships a Generic OpenAI provider with an open Base URL field, which is where Pareto plugs in. Fill in five fields and your workspace chats go to Pareto, which selects frontier and open models for each request and blends their outputs into one answer.

Choose Personal · $10/month See the setup →

Settings from AnythingLLM’s docs50M tokens a week

An illustration of AnythingLLM on Pareto. Not a screenshot.

Set it up in five fields

AnythingLLM sends chats to any server that speaks the OpenAI Chat Completions format through its Generic OpenAI provider. Fill it in once under LLM Preference, or set the matching variables in .env if you run AnythingLLM in Docker.

  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 LLM Preference

    Open settings from the bottom of the sidebar, go to AI Providers > LLM, and search the provider list for Generic OpenAI.

  3. Fill in the connection

    Set Base URL to https://api.unbiased.ai/v1 (keep the /v1), paste your key into API Key, and type pareto into Selected Model.

  4. Set the limits and save

    Set Model context window to 1000000 and raise Max Tokens from its default of 1024 to something like 4096, so long answers are not cut short. A larger context window lets AnythingLLM pack more history and document text into each request, and bigger requests use more of your weekly tokens. Save, then open a workspace and chat.

Settings follow AnythingLLM’s own documentation: AnythingLLM docs: Generic OpenAI LLM provider.

LLM Preference > Generic OpenAI
Base URL:              https://api.unbiased.ai/v1
API Key:               your-unbiased-api-key
Selected Model:        pareto
Model context window:  1000000
Max Tokens:            4096
Or .env (Docker)
LLM_PROVIDER='generic-openai'
GENERIC_OPEN_AI_BASE_PATH='https://api.unbiased.ai/v1'
GENERIC_OPEN_AI_API_KEY='your-unbiased-api-key'
GENERIC_OPEN_AI_MODEL_PREF='pareto'
GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=1000000
GENERIC_OPEN_AI_MAX_TOKENS=4096

Pareto replaces the chat model only. Your Embedder and vector database settings stay as they were. The field labels and .env keys come from AnythingLLM’s source; see its .env.example for the Generic OpenAI variables.

AnythingLLM stays. The model changes.

One provider setting changes. Everything you have built inside AnythingLLM stays where it is.

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 AnythingLLM 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 AnythingLLM by the month

One API key works across AnythingLLM 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.

AnythingLLM on Pareto, questions answered

Which LLM provider do I choose in AnythingLLM?

Choose Generic OpenAI. It is AnythingLLM’s provider for any OpenAI-compatible service, and Unbiased speaks the OpenAI Chat Completions format it uses. AnythingLLM’s docs describe it as a developer-focused provider, so type each field carefully: a wrong Base URL or model name shows up as chats that fail.

What goes in Selected Model?

Type pareto. Unbiased does not publish a model list, so do not wait for one. AnythingLLM shows a text box when no list comes back; if it shows a dropdown without pareto in it, set GENERIC_OPEN_AI_MODEL_PREF='pareto' in .env instead.

Why do answers stop partway through?

AnythingLLM sends Max Tokens with every request, and the form’s default is 1024. Raise it to 4096 or more. Pareto accepts up to 131072 output tokens per request.

Does @agent use Pareto too?

Each workspace can set its own Workspace Agent LLM Provider. If yours is set to something else, point it at Generic OpenAI and pareto as well. We have not tested AnythingLLM’s agent skills against Pareto, and format compatibility is not a promise that every feature works, so tell us if one doesn’t.

Does Pareto handle embeddings for my documents?

No. Embeddings are a separate setting under AI Providers > Embedder, and Pareto does not replace it. Keep the embedder you use today.

Is Pareto made by the AnythingLLM team?

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

Fill in five fields, then ask your documents something hard

One provider, one key and the workspaces you already have. Pareto starts at $10 a month for 50M tokens a week.

Choose Personal · $10/month See the setup →