300 Etsy photos: Nano Banana 2.1 vs GPT Image 2.5, cost on Sume

The short answer

Thirty Etsy listings with ten photos each is 300 images. On Sume that costs $30.00 on Nano Banana 2.1 at 1K ($0.10 each), $45.00 at 2K ($0.15 each), and $16.69 on GPT Image 2.5 medium at 2K ($0.055625 each, rounded to the cent). The cheapest row, GPT Image 2.5 low at 1K, is $7.43.

Nano Banana 2.1 launched on 2026-10-06 and Google lists $0.0336 for a 1K image, so the launch-week question for a seller is whether the Sume premium is worth it. The answer depends on whether you need Google's own price or one key that also reaches GPT Image 2.5.

The arithmetic

Etsy sellers usually need a hero image, a few lifestyle scenes and some detail crops per listing, which is why ten per listing is a common plan. The table prices the whole 300-image catalog refresh once, at the Sume list prices read from the public catalog, and adds Google's standard rate as a reference row you cannot buy through Sume.

Each Sume line is the count times the per-image price, and Sume's prices already include its margin of 1.25 on the provider list price.

How to run it

Split the job by listing so a failure costs one listing, not the catalog. Use n to get several variants per call, and remember the per-model ceiling is below 10 for some models, so read the range first.

If a listing needs a precise product, send the real photo as an input reference and ask for a new background. GPT Image 2.5 takes up to 16 references; read the input_references range for any other model if a listing has many angles.

Retries and cost per listing

Some images will be rejected by eye, and rejected images are billed like any other, so budget a margin. The bullets add 20 percent to each Sume total in the table above (the totals multiplied by 1.2) and divide by the number of listings to give a per-listing cost.

Treat the per-listing figure as the number to compare across models, because it does not change when the count changes. Re-read the public catalog before a large run, since prices can change and the table is a snapshot from 2026-10-08.

• Nano Banana 2.1 at 1K: $30.00 becomes $36.00 with 20 percent extra images, which is $1.20 per listing (a 30-listing job).
• Nano Banana 2.1 at 2K: $45.00 becomes $54.00 with 20 percent extra images, which is $1.80 per listing (a 30-listing job).
• GPT Image 2.5 medium (2K): $16.69 becomes $20.03 with 20 percent extra images, which is $0.67 per listing (a 30-listing job).
• GPT Image 2.5 low (1K): $7.43 becomes $8.92 with 20 percent extra images, which is $0.30 per listing (a 30-listing job).

What the docs say to check

The endpoint pricing lines are what Sume charges your wallet and already include the Sume margin, so a call costs cost_usd times n. Sume bills image generation all or nothing: a generation that fails or is cancelled is not charged.

The n parameter takes up to 10 images per call, but per-model ceilings are lower, so read the n range descriptor for the model before you plan the number of calls.

Google direct is cheaper per image at every size. Sume is the path when you want pay-as-you-go from one wallet and the same call shape across models, not the lowest per-image rate.

Every price in this post is a snapshot dated 2026-10-08. The Sume figures come from the public catalog and the Image API docs, the Google figures come from its Gemini API pricing page, and no figure here is a benchmark of quality or speed. Prices and model lists change, so confirm them on the day you spend money.