Nano Banana 2.1, 1,000 images: Sume row vs Google's standard and batch
1,000 Nano Banana 2.1 images at 2K: $150 on Sume's row, $50.40 at Google's standard rate, $25.20 at Google's batch rate, per each page read 2026-10-09.

A thousand Nano Banana 2.1 images at 2K cost $150 through Sume's catalog row ($0.15 each), $50.40 at Google's published Gemini API standard rate ($0.0504 each) and $25.20 at Google's batch rate ($0.0252 each), as read on 2026-10-09. The three numbers are different offers, not one price with a markup, so the useful question is what each one includes.
The numbers side by side
Google's pricing page states output image prices per image: standard $0.0336 (1K), $0.0504 (2K) and $0.113 (4K); batch $0.0168, $0.0252 and $0.0567. Sume's catalog lists nano-banana-2.1 at $0.075 (0.5K), $0.10 (1K), $0.15 (2K) and $0.20 (4K). Multiplying each by 1,000:
| Size | Google standard | Google batch | Sume catalog row |
|---|---|---|---|
| 1K | $33.60 | $16.80 | $100.00 |
| 2K | $50.40 | $25.20 | $150.00 |
| 4K | $113.00 | $56.70 | $200.00 |
What the gap does and does not mean
Dividing the 4K row, Sume's $0.20 is 1.77 times Google's standard $0.113. That ratio is not Sume's margin: Sume prices each model from the provider list it actually calls, with a 1.25 multiplier, and the repo's price list does not claim to mirror Google's direct API table. Compare the offers on what you need, not on the ratio.
Reasons to pay the Sume row: one API and one wallet across image, video, audio and timeline jobs, the same job and webhook model for every model, and no separate Google billing set-up. Reasons to go direct: you only generate Gemini images and can use batch for non-urgent work, where Google's batch rate is half of its standard rate on every size.
- Google's page bases output on tokens: 1,120 tokens for a 1K image, at $30 per million (standard) or $15 per million (batch).
- The catalog entries I read do not describe a batch tier for this model.
- Re-read both pages before budgeting; neither price is frozen.
Worked example for 250 images
A smaller run shows the same pattern. Two hundred and fifty 1K images cost 250 x $0.10 = $25.00 on Sume's row, 250 x $0.0336 = $8.40 at Google's standard rate and 250 x $0.0168 = $4.20 at its batch rate. If your usage is that small, the absolute difference is $20.80 between the extremes, and the time you spend on a second vendor's billing and keys may cost more than that.
At 10,000 images a month at 2K the extremes are $1,500 on Sume against $504 and $252 at Google's standard and batch rates. At that volume it is worth asking whether you need the shared wallet and job model enough to pay for it.
Sources
Google's rates are from the Gemini API pricing page. Sume's are from the catalog; see also the image model docs.
Sources
Related posts
More in Pricing
- Nano Banana 2.1 for 37 images: Google's price vs Sume at 1K, 2K, 4K
A 37-image set on Nano Banana 2.1 costs $1.24 to $4.18 at Google's list and $3.70 to $7.40 on Sume. Per-tier arithmetic and what the gap buys you.
- Nano Banana 2.1 4K is 3,780 tokens, 3.4x the 1K cost: Google vs Sume
Google prices Nano Banana 2.1 by image tokens: 1,120 at 1K, 1,680 at 2K, 3,780 at 4K. Sume bills a flat tier price instead. Both price ladders, side by side.
- Nano Banana 2.1 edit vs generate on Sume: same price per image by tier
Do reference images change the Nano Banana 2.1 price on Sume? The estimator reads tier and image count only: $0.075 to $0.20 per image, edit or not.
- Nano Banana 2.1 has no free tier on Google: what Sume bills instead
Google lists the Nano Banana 2.1 free tier as Not available. A look at paid per-image prices, what Google's figure leaves out, and Sume's flat billed price.
Written by Sume