A few days ago someone asked it directly: you say the software is free, so how do you make money? Are you going to charge per device later?
Someone asked the same thing last month. “Free” on the market usually means one of two things. The features are cut down, and while you use it you are told to upgrade. Or the first three months cost nothing, and after that there is a monthly fee.
The software itself is free
The iEasyRun software for controlling a phone with AI is completely free. There is no paywall, no charge per device, and no charge per task. Install it locally from installation selection, and the feature set is complete.
The software sits on your own computer and does not use our servers, so there is no monthly fee. Task records, screenshots, and assets stay on your machine. There is no storage fee either.
The separate cost is the language model. We do not provide one.
Which operations need a model, and which do not
The installation tutorial states a hard requirement: add and save a language model before conversation can drive the phone.
Two things use it.
AI conversation. You describe a task in Chinese. It has to understand what you said, plan the order of steps, and decide how each step is done. Understanding and planning go through the language model.
Having the AI write a flow. Generating or editing steps on the workflow canvas also goes through the conversation model.
Running a workflow that is already saved does not use it. Per the official technical docs, a trial run and a run of a saved workflow go through a local step engine. They do not call the conversation model, they do not consume conversation tokens, and they do not need a model API connected.
A scheduled task does not go through it either. A scheduled trigger and a manual run are the same execution chain, and neither consumes conversation tokens.
Generating the flow that one time costs money. After the flow is saved as a template, repeat runs no longer go through the conversation model. The earlier you save it, the less you pay for conversation later.
If you drive the phone through conversation every day and describe the task again each time, you pay for a call every time, and you wait for the planning every time.
On the capabilities and models page, models fall into two types:
| Type | What it does | When it is used |
|---|---|---|
| Conversation model | Understands what you say, plans the task, generates steps | AI conversation, and AI generating or editing a flow |
| VLM vision model | Reads a screenshot and decides where to tap | When the next step depends on looking at the screen |
The conversation model does the thinking. The VLM does the looking. Each side can use a different provider. The interface includes models such as qwen. Fill in the API key and address you applied for yourself.
The model API bill is paid to the provider you chose. It does not pass through us. You are charged for what you use, at the provider’s price.
How to hold the cost down, and what a month comes to
If a task can become a workflow, make it one. Once a flow is saved as a template, repeat runs no longer create a conversation charge. The same job run three times in conversation today, versus paying once to make the template and then running it thirty times, can differ by tens of times.
Talk a complex task through before you run it. One vague instruction goes off course. You describe it again, it goes off course again, and you edit it again. Those rounds of conversation add up to more than thinking it through once. Use refine mode to get the requirement clear, then send it.
Pick the model by the task. A simple task can stay on a cheaper small model. Use a large model when the planning is complex.
There is no single monthly figure, because usage differs. Two ways of using it sit side by side.
When the daily tasks are all saved as workflows, you run workflows every day and do not use conversation, and the model bill is close to zero. Writing a new flow now and then costs a little, and per use that amount is small.
When you drive phones through conversation a lot every day, the cost depends on two things: the model price, and how complex the tasks are. The same task on a different model can cost several times as much.
Take a task you do every day, run it once in conversation, and see what that run used. Then turn it into a workflow, run it ten times, and see what that used. Put the two numbers next to each other and you have your own account.
The software runs on your own computer. The server cost is not on our side, so the software itself is free. The only thing that costs money is the model. After a flow is saved as a template, repeat runs no longer go through the conversation model.
Frequently asked questions
- Is the software genuinely free, with no hidden charges?
- The iEasyRun software itself is completely free, with no paywall and no charge per device or per task. It runs on your own computer, so there is no trial period, and no threshold after which you have to upgrade.
- So where does money go?
- To the language model. iEasyRun does not sell models, so you supply your own API key and pay your chosen provider directly for inference. That is the only recurring cost, and it is usage-based.
- Can I use it without configuring a model?
- It depends on the task. Running saved workflows needs no model and no model API call. But using Chinese conversation to have AI plan a task, or having AI generate and edit flows, requires a model configured on the capabilities page first.
- Do workflows consume tokens?
- Per the official technical documentation, trial runs and saved workflow runs go through a local step engine. They do not call the conversation model, do not consume conversation tokens, and do not require a model API. Only AI conversation and AI-generated or AI-edited flows use the conversation model.
- Are the conversation model and the VLM two different things?
- Yes, and they do different jobs. The conversation model understands what you say, plans the task and generates steps. The VLM reads screen captures and helps decide where to tap. They can come from different providers and are configured in the model section of the capabilities page.
- How do I choose a cheaper model?
- Two approaches. Turn recurring work into workflows, since running a workflow consumes no tokens and you pay once when creating it. And for complex tasks, talk the requirement through in refinement mode before executing, which cuts the trial-and-error cycles where the real spend happens.
- What does a month cost?
- There is no single number, because usage varies so much. If you turn everything into workflows, daily execution costs almost nothing and you only spend a small amount occasionally when writing a new flow. If you drive phones through conversation heavily every day, it depends on your model price and task complexity.
- Do screenshots add cost?
- It depends on the task. Anything requiring a VLM to read the screen calls a vision model, and that is billed by image. Tasks that do not depend on reading the screen, such as pure tapping and typing, incur no model cost from screenshots.
Work out the numbers first
The software is free, install it and see what you use
Runs locally with no server to buy. Bring your own model API key and pay only for what you use.