Nano Banana Pro (Gemini 3 Pro Image Preview)
Google · released Nov 20, 2025
- Type
- Closed
- Input
- $2.00
- Output
- $12.00
- Cached
- None held
List price · per 1M tokens · Google AI Studio at 66K context · source ↗
Our take
Written Sep 1, 2026Nano Banana Pro is Google's proprietary image-generation and editing model, accessed through two hosted endpoints. It can handle up to 65,536 tokens in a single request, giving room for detailed visual instructions and reference images.
Pick this for image generation or editing tasks that need long, detailed prompts with multiple reference images or iterative instructions. Choose the Google AI Studio endpoint if speed matters, since throughput there is confirmed at 75 tokens per second. Skip it if you need verified quality scores, if you want to self-host, or if you are cost-sensitive to output pricing.
The case for it
- 65,536-token request limit — unusually spacious for image-generation prompts, fitting detailed visual descriptions plus reference images and editing instructions.
- Two hosted endpoints available, with confirmed throughput on one.
The case against it
- Expensive output tier with no measured quality data to justify the cost.
- Throughput unverified for one of two providers; only one endpoint has confirmed speed data.
- Proprietary only — no download option, and parameter count undisclosed.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked between 2 hours and 2 months ago — each listing carries its own date.
Google AI Studio, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Google AI Studio on 66K of context.
- per 1M tokens
- $2.00 in / $12.00 out
- Context served
- 66K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $12.00checked 2 hours ago | 66K | not measured | Unknown | Unknown | Unknown |
| Google AI StudioglobalThrough OpenRouter | $2.00 / $12.00checked 2 months ago | 66K | not measured | No | Yes55 days | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| Google AI StudioglobalThrough OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text and images in, text and images out
- Catalogue slug
- google-nano-banana-pro-gemini-3-pro-image-preview