Nano Banana Pro (Gemini 3 Pro Image)
Google · released Jun 18, 2026
- Type
- Proprietary
- Input
- $2.00
- Output
- $12.00
- Cached
- $0.20
List price · per 1M tokens · Google AI Studio at 131K context · source ↗
Our take
Written Aug 2, 2026Google's Gemini 3 Pro Image is an image-generation model that accepts text and images to produce both text and images. It can accept a large request for an image model and is available only through Google's own services and OpenRouter.
Use this for image generation and editing where prompt fidelity matters more than cost, or multimodal pipelines that mix image understanding and image output in one call. Skip it if you want a broad choice of hosts or predictable per-image pricing.
The case for it
- Native image output within the Gemini API surface.
- Large request limit for an image model: supports long, detailed prompts and reference-image context.
The case against it
- Google-only availability: Vertex, AI Studio and OpenRouter, which routes back to Google.
- Token-based pricing makes per-image cost hard to predict.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Nano Banana Pro (Gemini 3 Pro Image) — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes Google AI Studio's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $2.00 in / $12.00 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.00 / $12.00 | 131K | not measured | Unknown | Unknown | Unknown |
| Google Vertex AIglobal | $2.00 / $12.00 | 66K | 51 tok/s | No | No | Confirmed |
| Google AI Studioglobal | $2.00 / $12.00 | 131K | 78 tok/s | No | Yes55 days | Unknown |
Across the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobal | ✗ | ✓ | ✓ |
| Google AI Studioglobal | ✓ | ✓ | ✓ |
Tool calling: 2 of 3 listings say yes, 1 says no. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, 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 3 listings do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image->text+image
- Catalogue slug
- google-nano-banana-pro-gemini-3-pro-image