120 Nano Banana 2.1 2K hero images: $6.05 at Google, $18.00 on Sume
Google lists Nano Banana 2.1 at $0.0504 per 2K image; Sume lists $0.15. For 120 listing hero images that is $6.05 versus $18.00, plus what the difference buys.

For 120 listing hero images at 2K, Google's Gemini API standard price for Nano Banana 2.1 is $0.0504 per image, which is $6.048, about $6.05. Sume lists nano-banana-2.1 at $0.15 per 2K image, which is $18.00. The gap is $11.95 for the batch. Choose by what you need around the image call, not only the unit price.
The two price lists
Google's pricing page (read 2026-10-09) lists Nano Banana 2.1 at $0.0336 per 1K image, $0.0504 per 2K image and $0.113 per 4K image on the standard tier, and $0.0168, $0.0252 and $0.0567 on the batch tier. Sume's public catalog lists nano-banana-2.1 at $0.075 for 0.5K, $0.10 for 1K, $0.15 for 2K and $0.20 for 4K.
Those are separate price lists from separate sellers. Sume's number is what a Sume workspace is charged; Google's is what a direct Gemini API account is charged. This post does not explain how Sume derives its figure; read the catalog for the live value.
| Option | Per image | Arithmetic | 120 images |
|---|---|---|---|
| Google standard | $0.0504 | 120 x 0.0504 | $6.05 |
| Google batch | $0.0252 | 120 x 0.0252 | $3.02 |
| Sume | $0.15 | 120 x 0.15 | $18.00 |
What you get on the Sume side
A Sume image job returns a job envelope with durable media.sume.com artifacts, polled at GET /v1/jobs/:id/status and /result. The same API key and credit balance cover video, audio and timeline work, so the hero image can feed an image-to-video call or a Timeline slot without moving files between vendors.
The Image API takes aspect_ratio including 4:5, 1:1 and 16:9, and reference images for edits. Reference URLs must be public HTTPS. If a listing set needs a hero, three angles and a short clip, one account and one receipt is the practical benefit.
How to decide
If you only need still images in bulk and have a direct Google account, the batch tier is the lowest number on this page: $3.02 for the same 120 images. If the stills are one step in a pipeline that also renders video and audio, add up the whole pipeline on one invoice before comparing a single line.
Whichever route you pick, check the price on the day you run it. Both lists change, and this comparison is only valid as of 2026-10-09.
A practical note
Run the numbers on your own mix before you decide. If half of the 120 images are 1K and half 2K, Google standard is 60 times $0.0336 plus 60 times $0.0504, which is $5.04, and Sume is 60 times $0.10 plus 60 times $0.15, which is $15.00. Add the time you spend moving files between systems and the cost of retries, and compare the invoice you would receive with the invoice you want. Both providers can change prices, so record the date next to your estimate.
Before you scale
Every price in this post is a Sume list price read from the public catalog on 2026-10-09, and the arithmetic is shown so you can redo it with your own counts. Rates can change, so re-read the catalog before a large batch and run a small test first. Sume bills the job's captured amount, and the job result tells you what was used, so compare the first run's receipt with your estimate before you scale the work to the full set.
Sources
Related posts
More in Use cases
- Nano Banana 2.1 product photo 1:1: 1024, 2048, 4096 and cost per tier
Square product shots with Nano Banana 2.1: 1024, 2048 and 4096 px sizes, what each costs on Sume, and what you cannot do, such as transparent output.
- Nano Banana 2.1 still, then Omni 1080p for 6 s: $1.225 together
A Nano Banana 2.1 still at $0.10 and a 6-second Omni Flash 1080p animation at $1.125 total $1.225 on Sume. The two-call Python script and where the cost sits.
- Narrate a Claude Motion explainer with Sume TTS and Timeline: 12 cents
A 450-character voiceover costs $0.021 on Sume TTS and a one-minute Timeline render $0.10, so narrating a Claude Motion MP4 comes to about $0.12.
- 90-Second News Explainer Video: Stills, Voiceover, Timeline, $1.06
How to build a 90-second vertical explainer on a current story with Sume: research calls, six stills, 1,200 characters of voiceover, one two-minute render.
Written by Sume