Skip to content
Milly Lab
Sign up

Start here

Getting Started Guide

This guide takes you from creating a Milly Lab account to your first useful result. It is for new users. It should take about ten minutes.

Last updated:


Create an account #

Go to https://app.m-lab.app/signup and choose one of:

  • Sign up with email — enter your name, email address and a password. Milly Lab sends a verification email; open it and follow the link.
  • Continue with Google — no password to manage. Milly Lab receives your email address, name and profile picture from Google.

If the verification email does not arrive, check your spam folder before requesting another.

A new account starts on the free tier: 10 messages per model every 4 hours on Luna · GPT-6 and DeepSeek Flash, with no card required. Paid plans start at $12 per month; see "Plans, Billing & Usage".


Find your way around #

After signing in you land on the dashboard at /app. The main areas:

AreaPathWhat it is for
Chat/app/chatConversation with a single model
Swarm Mind/app/swarmEntry point for the two multi-model modes
Project Mode/app/projectOne task, decomposed and executed by a team of models
Council Mode/app/councilSeveral models answering the same brief independently
Light Studio/app/light-studioImage generation
Video Studio/app/video-studioVideo generation
3D Studio/app/studio-3d3D asset generation
Spaces/app/spacesOrganising your work into collections
Settings/app/settingsProfile, billing, team, model preferences

Send your first message #

  1. Open Chat.
  2. Pick a model from the selector.
  3. Type your question and press Enter.

The response streams in as it is generated. You can attach files, use voice input, and turn on web search — those are covered in the Feature Guides.

Start on a small model. Luna · GPT-6 or DeepSeek Flash are fast and cheap, and answer most questions perfectly well. Reach for a larger model when a small one has actually disappointed you, not before.


Choosing a model #

There is no single best model. The trade-off is speed and cost against depth.

When you wantTry
A quick factual answer, a summary, a rewriteLuna · GPT-6, DeepSeek Flash, Claude Haiku 5.5
Everyday work — drafting, analysis, ordinary codeClaude Sonnet 5.5, Terra · GPT-6.1, DeepSeek Flash
Hard reasoning, tricky debuggingDeepSeek V4 Pro in Chat; Sol · GPT-6.1, Claude Opus 5.5 and Sol · GPT-6 in Swarm Mind
A very long document or codebase in one goGemini 3.8 Flash, Gemini 3.8 Flash 200K

Sol · GPT-6.1, Claude Opus 5.5 and Sol · GPT-6 are offered in Swarm Mind (Project and Council Mode), not in the Chat model selector.

Which of these you have depends on your plan. Plans are not cumulative — each includes its own specific set of models, so a higher plan is not a superset of a lower one. See "Plans, Billing & Usage".

If a model is greyed out, it is not in your plan.


Understanding the allowance meter #

Your plan gives you a monthly allowance for each of its models, counted in messages (images or clips for the studios), and each model's allowance is separate. So you can use up Claude while GPT still has plenty left.

Check what remains at Settings → Billing (/app/settings/billing).

Two things to know now, so they do not surprise you later:

  • Cost grows as a conversation lengthens. The whole history is sent to the model each turn. Starting a new conversation for a new topic is cheaper as well as clearer.
  • Swarm Mind costs much more than chat. One brief becomes many model calls. Use it for work that genuinely needs several models, not for questions a single chat could answer.

If you run out, Milly Lab refuses the request rather than billing you silently. The full list of payment-required errors is in "Plans, Billing & Usage".


Try something bigger #

Once chat feels comfortable:

Generate an image. Open Light Studio, describe what you want, and generate. Reference images and batch generation are there when you need them.

Run a Council. Open Council Mode, write one brief, and let several models answer it independently. Useful when you want to compare approaches rather than accept the first answer. You can diff the answers and merge the best parts.

Run a Project. Open Project Mode and give it a task with several parts. An orchestrator breaks it into subtasks and worker models execute them, with a synthesized deliverable at the end.

Swarm Mind requires a Max plan or above.

Connect a repository. In Project or Council Mode you can connect GitHub or Google Drive so runs read your actual files and propose edits. Nothing is ever written without your explicit approval — read the Connected Workspaces Guide before you connect anything.


Set yourself up properly #

Worth doing once, in Settings:

  • Profile — set your interface language: English, Russian or Tajik.
  • Profile → Security — turn on two-factor authentication, and add a passkey if you like.
  • Billing — see your plan and what is left.
  • Team — if you are working with others, create a team and invite them.
  • Agents — set per-model preferences for response length and reasoning effort.

Getting a better result #

  • Say what you want, specifically. "Rewrite this paragraph for a non-technical reader, keeping it under 100 words" beats "improve this".
  • Give the model the material. Attach the file or paste the text rather than describing it.
  • Say what the output is for. A model writing for a board paper makes different choices than one writing a code comment.
  • Check the output. Models produce confident text that is sometimes wrong. Verify facts, figures and citations before you rely on them.
  • Leave web search off unless the answer depends on current information. It makes responses slower and costs more.

Where to go next #

You want toRead
Understand what your plan coversPlans, Billing & Usage
Connect GitHub or Google DriveConnected Workspaces Guide
Learn a specific surface in depthFeature Guides
Fix something that went wrongTroubleshooting & FAQ
Know what happens to your dataPrivacy Policy