Which Google image model for product photos after Oct 6?
Nano Banana 2.1, Pro or Lite for product photos? A table built from Google's Oct 6 prices, size limits and reference rules, and what Sume lists.

For most product photos, start with Nano Banana 2.1. It is $0.0504 per 2K image on Google's Standard tier, takes up to 10 object references, lists legible text rendering and goes to 4K. Choose Pro when you need style references or a premium look worth $0.134, and Lite only for 1K drafts. Sume lists 2.1 and Pro, but not Lite.
The table
Prices are Google list prices for one output image on the paid Standard tier. Capabilities come from Google's image guide.
| Need | Pick | Price per image | Why |
|---|---|---|---|
| Catalogue shots at 2K | Nano Banana 2.1 | $0.0504 | Up to 10 object references; 1K to 4K |
| Hero image at 4K | Nano Banana 2.1 or Pro | $0.113 or $0.24 | Both go to 4K |
| Brand look from a style image | Nano Banana Pro | $0.134 at 1K or 2K | Only Pro lists style references (up to 3) |
| Fast 1K drafts | Nano Banana 2 Lite | $0.0336 | 1K only, no grounding |
| Product with a current fact on it | Nano Banana 2.1 | $0.0504 at 2K + search fee | Supports Google Search grounding; Lite does not |
Cost of 100 product images at 2K
At 2K, 100 images cost $5.04 on Nano Banana 2.1 and $13.40 on Pro, from Google's prices. Lite cannot make 2K. The $8.36 gap is the price of Pro's style references and whatever look-and-feel difference you see in a side-by-side test.
What I would not claim
- That Pro looks better than 2.1 on your product. Google does not publish a ranking, so test five of your own prompts on both.
- That Lite is as good at text. Google says only that it is the fastest and cheapest, tuned for speed and scale.
Via Sume
Use google/nano-banana-2.1 or google/nano-banana-pro in Sume's Image API. Sume sets its own prices, so read usage.cost on a test image and GET /v1/images/models/{id}/endpoints before you quote a client.
Sources
Related posts
More in Use cases
- Wine bottle reveal clip: 6 seconds of Wan 3.0 from a label photo
Animate a bottle photo into a 6-second reveal with wan-3.0 on Sume: 38 cents at 480p, 75 cents at 720p, $1.50 at 1080p. Why the label needs checking.
- How do I make a winter tire changeover promo video for my garage?
Three 6-second Wan 3.0 clips, a 420-character voiceover, a duck-under music bed and booking captions for a garage: $2.695 on Sume at 720p.
- Write a lip-sync script in 5 to 14.8 second beats (H3 Max voice-over)
MiniMax H3 Max lip-sync on Sume takes audio of 5 to 14.8 seconds. Write the script in beats that fit the window, then voice each beat; the price per beat.
- Write the music brief after the voiceover, using TTS timestamps
Lyria on Sume takes no duration field, only time ranges in the prompt. Generate the voiceover first, read its word timings, then write the section markers.
Written by Sume