Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Google · released Feb 26, 2026
- Type
- Closed
- Input
- $0.50
- Output
- $3.00
- Cached
- None held
List price · per 1M tokens · Google AI Studio at 66K context · source ↗
Our take
Written Sep 1, 2026Nano Banana 2 is Google's proprietary image-generation and image-editing model, accessed through text and image prompts. It can handle up to 131,072 tokens in a single request for complex multimodal instructions, though no quality benchmarks have been measured yet.
Choose this when you need one model that both generates or edits images and writes explanatory text, or for long-form multimodal workflows needing substantial instruction context. Pick Google AI Studio if throughput matters, as it is the only provider disclosing speed. Skip it if you need measured quality scores, open weights, or verified speed from every provider you might use.
The case for it
- 131,072-token request limit gives substantial room for complex image-editing instructions.
- Same pricing across all three access points, so provider choice does not change cost.
- Google AI Studio discloses 146 tokens per second; the other two providers do not.
The case against it
- No benchmark scores in our data, so quality is unverified.
- Output costs six times more than input, a steep ratio for image-heavy workloads.
- Throughput is unverified for two of the three providers.
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 Vertex AI, through OpenRouter
Why this differs from the header. The strip above quotes Google AI Studio's own list price; this is the cheapest live offer, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.50 in / $3.00 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.50 / $3.00checked 2 hours ago | 66K | not measured | Unknown | Unknown | Unknown |
| Google Vertex AIglobalThrough OpenRouter | $0.50 / $3.00checked 2 months ago | 131K | not measured | No | No | Unknown |
| Google AI StudioThrough OpenRouter | $0.50 / $3.00checked 2 months ago | 66K | not measured | No | Yes55 days | Unknown |
OpenRouter
Google AI StudioAcross the 3 listings we hold: 2 say they do 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 Vertex AIglobalThrough OpenRouter | |||
| Google AI StudioThrough OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. JSON output: 2 of 3 listings say yes, 1 publishes no parameter list. Strict schema: 2 of 3 listings say yes, 1 publishes no parameter list.
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.
- 1 of 3 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- 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-2-gemini-3-1-flash-image-preview