Is the AI food scanner free?

Yes. Every account gets a free daily allowance of AI use, shared by the scanner, the coaches and the chat, and a scan costs a small fraction of it. If you use AI heavily enough to run out, it pauses until the next day, or you can add your own Google Gemini API key in Settings › AI, which has no limit and is billed by Google to you.

What gets sent when I scan a plate?

One photograph, resized to 1024 pixels wide, sent to Google's Gemini API. On the free allowance it passes through Base's server, which adds Base's key and stores nothing; with your own key it goes straight from your phone to Google. Nothing else goes with it: no training history, no log data. The photo is not kept by Base anywhere but on your phone.

How accurate is a photo calorie estimate?

Treat it as a starting point rather than a measurement. A photograph carries no weight information, so portion size is inferred from apparent volume and any scale reference in frame. Base explicitly warns when it could not find a scale reference, because that is the condition under which the estimate is least reliable. Every item is editable before you commit.

Can I edit what the scanner found?

Yes, and you should. The review list lets you rename any item, change its weight in grams, which rescales its macros proportionally, or remove it entirely. Nothing is written to your log until you commit the reviewed list.

Do I have to use the AI scanner?

No. It sends nothing unless you use it, and the first time you use any AI feature the app asks whether that is all right. Barcode scanning, search and Quick Add all work without it.

Log a Meal by Photo With the AI Scanner

Setting it up

There is nothing to set up. The first time you use the scanner, or any other AI feature, the app asks whether it may send your request to Google's Gemini. Say yes and it scans; say no and nothing is sent.

Every account gets a free daily allowance of AI use, and Settings › AI shows how much of today's is used. If you would rather use your own Gemini API key, from Google AI Studio, paste it there: your requests then go straight to Google on your key, with no daily limit.

What actually gets sent

One photograph, resized to 1024 pixels wide, sent to Google's Gemini API.

That is the whole payload. No training history, no food log, no device identifier. On the free allowance the photo passes through Base's server, which checks you are signed in, adds Base's key, forwards it to Google and stores none of it; the only thing the server keeps is a running total of what your AI use cost today. With your own key there is no Base server in the path at all.

The photo is not retained by Base anywhere but on your phone. See what Base does with your data for the complete picture.

Using it

The scanner's explainer, which a build with no AI available shows instead of half-working. It says what it would send and links to Settings.

Shoot the plate, or pick a photo from your library. The scan runs through three visible stages (camera, analysing, review) and any failure lands on an explicit error with a reason rather than an empty list.

The scale warning

If the model could not find a scale reference in the frame, Base says so before you review.

This matters more than any other caveat about photo estimation. A photograph carries no weight information whatsoever. Portion size is inferred from apparent volume, and apparent volume depends entirely on knowing how big something in the frame is. A bowl of rice photographed close up and a bowl of rice photographed from standing look identical to a model with nothing to calibrate against.

Practical fix: get something of known size in the shot. A fork, a standard dinner plate, a hand. It measurably improves the portion estimate and costs nothing.

Reviewing before committing

The review list is the part that makes the feature usable rather than merely impressive.

Action	Effect
Rename an item	Fixes a misidentification without losing its macros
Change grams	Rescales that item's macros proportionally from a stable baseline
Remove an item	Drops it entirely

The rescaling is linear off the original estimate rather than compounding, so nudging a portion up and back down returns exactly where you started:

detected:  chicken thigh, 180 g, 412 kcal
corrected: 130 g
scaled:    412 × (130 ÷ 180) = 298 kcal

A running total sits below the list so you can see the whole plate before committing.

When to use it, and when not to

Good for: restaurant meals, food someone else cooked, anything with no packaging and no obvious recipe, a plate you want logged in fifteen seconds rather than five minutes.

Bad for: anything with a barcode, which the barcode scanner handles far more accurately; anything you eat regularly, which is better saved as a meal; anything where the exact number matters, because the exact number is not what this produces.

The honest framing is that a photo estimate you actually log beats a precise entry you do not. Adaptive maintenance is computed from your average logged intake, so a missing meal shifts your measured maintenance permanently while a roughly-right meal barely moves it.

Common mistakes

Treating the output as measured. It is an estimate from a picture. The scale warning exists because Base knows when it is estimating badly, and it tells you.

Committing without reviewing. The review step is not a formality: misidentifications are common and take one tap to fix.

Shooting from directly overhead with nothing else in frame. That is the worst possible input for portion estimation. Angle it and include a utensil.

Using it for packaged food. A barcode gives you the manufacturer's own numbers. There is no contest.

Re-scanning the same home meal every day. Scan it once, correct it, then save the plate as a meal from the Meal tab. After that it is one tap and no network.

Scanning every snack on a heavy AI day. The free allowance is shared with the coaches and the chat. If you run out, the scanner says so and tells you when it resets; saved meals and barcodes never need it.

What to do next

If you eat out regularly, scan one restaurant meal to see how the review list behaves. If you mostly eat at home, skip this feature entirely: saved meals are faster, free and exact.