Real-life example: a very cheap setup with DeepSeek

What this example builds

One provider profile in SideNote Pro, pointed at DeepSeek, running deepseek-flash with thinking switched off, paid for with a five dollar top-up. That profile becomes your everyday assistant: the one that answers when you highlight a sentence and press Ctrl+Shift+E, the one that rewrites an email, and the one that reads a screenshot of an error dialog and tells you what it means.

It is a bring-your-own-key setup like any other, so nothing here is special-cased in SideNote Pro. If you would rather read the general version first, see what BYOK means. If you want the mechanics of any compatible endpoint, see configuring an OpenAI-compatible provider.

Why image input matters here

DeepSeek used to offer its fast model in two forms, a text model and an experimental vision variant. deepseek-flash ends that choice because it reads images natively. Image input is a model capability rather than an application one.

SideNote Pro can capture a region of your screen, take a bitmap off the clipboard with Ctrl+V, or accept an image dragged onto the window, and it will format all of them correctly for any OpenAI-compatible endpoint. Whether anything comes back depends entirely on the model you pointed it at. A text-only model ignores the image or refuses it, and the failure is quiet enough that people spend an afternoon blaming the app. See asking AI about a screenshot.

It is also a reason to keep the everyday profile on deepseek-flash even if you add DeepSeek's larger deepseek-v4-pro for harder work, because DeepSeek lists vision as not supported on that one. Vision is the difference between an assistant you can show things to and one you have to describe things to, and describing a broken layout, a spreadsheet region, a chart or a stack trace in a dialog box is slow and lossy work.

An error dialog you have never seen before

Capture it, ask what it is actually telling you and what the likely causes are.

A screenshot of a settings pane in some other application

Ask where the option you are hunting for lives.

A chart in a report

Ask what the trend is and what it does not show.

A photo or scan of a printed page

There is no OCR in SideNote Pro, so whatever text gets read is read by the model's own vision. A text-only model reads nothing at all.

A region of a spreadsheet

Faster to capture than to retype, and the numbers come along with their layout.

What five dollars actually buys

This is the part people do not believe until they try it. For ordinary desktop assistant use, a five dollar top-up on a cheap fast model lasts months. Not a week, not a fortnight. Months.

The arithmetic behind that is simple. deepseek-flash is priced in cents per million input tokens and about a dollar per million output tokens, and the requests you actually send all day are small: a highlighted paragraph and an instruction, a short email to rewrite, a two line question about a screenshot. A request like that is hundreds or a few thousand tokens, not hundreds of thousands.

Off-peak is half price, and it covers more of the week than peak does: peak is 01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays, and everything else, including weekends and Chinese public holidays, is off-peak. Input DeepSeek has already seen, such as the earlier turns of a conversation you are continuing, is usually billed at the cache-hit rate, fifty times lower. DeepSeek caches automatically, so there is nothing to switch on.

At the peak rate, five dollars covers a little over four thousand requests of that size. At twenty a day, that is more than six months.

In practice five dollars really does go a very long way, and how long depends on how you use it. Someone asking twenty short questions a day will not come close to finishing five dollars in a quarter. Someone attaching a hundred page PDF every morning and never starting a new thread will get through it much faster. The habits in reducing your AI API costs are what decide which of those two you are.

Fast enough to use without thinking about it

The second reason to pick a flash-class model for the everyday slot is latency. A docked assistant only earns its place if answering a question is quicker than opening a browser tab, and that means the answer should start appearing more or less as you finish reading your own question.

Small fast models are very good at exactly the work that dominates daily use: explaining a sentence, rewriting a paragraph, summarizing a page, translating ordinary prose, generating a few subject line options, telling you what a screenshot shows. None of that has hidden structure to reason about, so a heavyweight model would give you the same answer, later, for more money. See when to use high reasoning effort for where the opposite is true.

Set Reasoning effort to None for this profile, and do not leave it on Provider default. On deepseek-flash the two are opposites. DeepSeek's default is thinking mode at high effort, so Provider default, which leaves the field out of the request, gets a round of hidden reasoning before every answer. Thinking increases the number of tokens the model generates, so leaving it on can make every request cost more. DeepSeek's API reference documents none as switching thinking off, so here None means exactly what it says.

Thinking is still there for the questions that need it, and any other level turns it back on: DeepSeek runs Minimal and Low as low effort, Medium, High and Extra high as high, and Maximum as max. Keeping that on a second profile is tidier than switching this one back and forth. While DeepSeek thinks, the answer area simply waits, because SideNote Pro shows the answer and not the reasoning behind it. Reasoning effort explained covers what each setting sends.

Step one: the DeepSeek account and the API key

This happens on the provider's side, in a browser, and takes a few minutes. Go to platform.deepseek.com. This is the developer platform, which is a separate thing from any consumer chat product: a chat subscription does not include API credit.

1. Create an account and sign in to the platformUse an email you will still have access to in a year, because it is the account that owns the billing.
2. Top up a small amountFive dollars is the whole point of this example. Start there. You can always add more, and starting small means an accident costs five dollars rather than fifty.
3. Set a spending limit if the dashboard offers oneDo it now rather than later. A cap on the provider side is the only limit that is authoritative, because it is the only one that sees every application using that key.
4. Create an API key and copy it immediatelyProviders typically show a secret key once and never again. Copy it straight into SideNote Pro, or into your password manager on the way.
5. Find the exact model ID in the model listIDs are case-sensitive and occasionally carry a version suffix. Copy the string the provider documents rather than typing what you remember.

Step two: the profile in SideNote Pro

Now the easy half. Open Settings, then AI providers, add a profile, and choose DeepSeek from the Provider list. The endpoint arrives with that choice. Unlike an OpenAI profile, a DeepSeek one starts with Model empty and Reasoning effort on Provider default, so three values are yours to set: the key, the model and the reasoning effort.

DeepSeek speaks the OpenAI-compatible Chat Completions API that SideNote Pro is built against, so there is nothing to adapt and no plugin to install. Choosing DeepSeek fills in the endpoint for you. It remains an editable field: if your requests go out through a company gateway or a proxy, put that address in instead and the rest of the profile is unchanged. See setting up any AI provider for presets, editable endpoints and typed model IDs.

Name the profile for what it is for rather than for the model inside it. Models change and prices fall; a profile called Everyday survives swapping the model underneath it. One called DeepSeek V4 Flash Vision became a small lie on 10 September 2026, when DeepSeek retired the model it was named after.

Settings › Setup guide

Step three: test before you trust it

Select Test & Load models. It calls GET https://api.deepseek.com/models with your key as a bearer token, and a pass tells you two things at once: the key is valid, and the model IDs that came back can now fill the picker, so you choose deepseek-flash from a list instead of trusting your typing. If you would rather skip it, type deepseek-flash into Model yourself. That works exactly as well.

Then send something real. Highlight a sentence anywhere in Windows, press Ctrl+Shift+E to explain it, and watch the answer stream in. Capture a region of your screen and ask what it shows. Those two checks confirm the parts of the setup that matter: text in, images in, streamed text back.

Step four: record the prices, so the ledger is worth reading

SideNote Pro tracks token counts locally, but it cannot know what your provider charges unless you tell it. It takes one input and one output price per model, in USD per million tokens, while DeepSeek's rates change with the time of day and with caching. Enter the peak rates, 0.30 and 1.20 as of 23 September 2026, so the estimate errs high rather than low: whatever you send off-peak, and any input served from DeepSeek's cache, costs less than it shows. With prices in, the usage view turns from a token counter into a spending estimate you can act on.

Settings › AI providers › Model pricing

Settings › Usage & cost

Optionally, switch on the local daily estimate limit as a seatbelt. It is a local guard working from local estimates and it cannot see other applications using the same key, so it complements the cap in the provider dashboard rather than replacing it. See usage and cost tracking.

What the profile is good at, and what it is not

A cheap flash model is not a compromise for most of what a docked assistant does. It is the correct tool. Its edges still matter, because the failure mode of a budget setup is trusting it on the one task it is bad at.

The practical shape of that is a second profile. Keep this DeepSeek profile as your default, and add a Deep profile on a stronger model with reasoning effort raised, for the handful of problems a week that genuinely need it. Duplicate copies the key and base URL, so building the second one is a two minute job, and switching between them is one click in the composer picker.

Settings › AI providers

Escalating beats starting deep. Ask the cheap fast profile first, because most problems that look hard are not, and you find that out in about three seconds. Switch profiles only when the answer is visibly shallow. Done that way you pay top-tier rates only on the problems that turned out to need them, which is the entire argument of setting up a model for each kind of task.

Five habits that stretch the five dollars

1. Start a new thread for a new topic. Ctrl+N. Every turn re-sends the accumulated history, so turn thirty of one endless thread is paying for twenty-nine turns of irrelevance.
2. Detach a document when you are finished with it. A large PDF is a large input on every later turn of that thread, not just the first one.
3. Ask for a length. In three bullets or under 100 words. Output tokens are the expensive ones, and a model told to be brief usually answers better because it has to decide what matters.
4. Edit and resend rather than arguing. Three corrective turns cost three round trips and drag all three into every request that follows. Fixing the original question costs one.
5. Crop the screenshot. Region capture rather than a full desktop grab. Fewer pixels is a smaller image payload, and a tight crop also gets you a better answer because there is less for the model to be distracted by.

None of these is a sacrifice. They all make the assistant better as well as cheaper, which is the usual sign that a cost habit is a good one.

Things worth knowing before you commit

A hosted provider is a hosted provider

Whatever you send goes to DeepSeek, under their terms and their jurisdiction, exactly as it would with any other hosted API. If the material is confidential, that is a decision to make deliberately.

For confidential work, add a local profile

Ollama or LM Studio costs nothing per token and never leaves the machine. Having it already configured is what makes the right choice the easy one at the moment you need it.

Compatibility is about the request format

OpenAI-compatible means streaming chat/completions works. It does not promise every optional field behaves identically. reasoning_effort is an example: DeepSeek documents none as switching thinking off and thinks at high effort without the field, while another compatible provider may ignore it or refuse the request.

Model IDs move

DeepSeek retired deepseek-v4-flash-vision-exp less than three weeks after releasing it. If requests start failing on a setup that worked yesterday, select Test & Load models again and check the current ID before assuming anything is broken.

Credit can simply run out

DeepSeek uses HTTP 402 for an empty balance, but SideNote Pro 1.13 recognises it as billing and tells you the provider account needs credit instead of showing a raw HTTP error. Check the dashboard and top up.

For most everyday requests, this five dollar, ten minute DeepSeek setup gives you a fast Windows AI assistant docked beside your work that can read screenshots you attach. Check model IDs, credit and where confidential material goes as you use it.