Google: Nano Banana Pro (Gemini 3 Pro Image)
google/gemini-3-pro-image
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Gemini 3 Pro Image, listed on OpenRouter as Nano Banana Pro, is Google's image-generation and editing model built on Gemini 3 Pro. The catalog reports text-and-image inputs with text-and-image outputs, a 131,072-token context window, and mandatory reasoning that cannot be disabled. It also exposes tuning, tool-calling and structured-output parameters. According to the vendor description carried by the catalog, it improves multimodal reasoning and real-world grounding over the earlier Nano Banana. Since evidence comes only from the OpenRouter listing, validate capabilities on your own workload.[1]
Strengths
- Accepts text and images as input and can return text or images, according to the OpenRouter catalog.[1]
- Large 131,072-token context window reported in the catalog, useful for combining long prompts with images.[1]
- The catalog lists parameters such as seed, structured outputs, tool calling and sampling controls.[1]
Limitations
- Evidence comes only from the OpenRouter catalog; an independent model card was not available in this source pack, so capabilities are source-reported rather than measured.[1]
- No benchmark results are listed, so generation and editing quality cannot be verified from this evidence; test on your own workload.[1]
- Reasoning is mandatory in the catalog configuration and no effort levels are listed, which may affect latency and cost control.[1]
Where to use it
- Reasonable candidate for image generation and editing workflows that mix visual inputs with text instructions; confirm quality on representative tasks.[1]
- Worth evaluating for applications needing tool-assisted or structured image pipelines, since the catalog lists tools and structured outputs.[1]
- Consider for multimodal assistants that must reason over images, as reasoning is always enabled; weigh the cost of that mandatory step.[1]
Sources
- [1] OpenRouter catalog · Google: Nano Banana Pro (Gemini 3 Pro Image)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Specifications
- Model ID
- google/gemini-3-pro-image
- Canonical ID
- google/gemini-3-pro-image-20260528
- Creator
- Added to OpenRouter
- 18.06.2026
- Context length
- 131,072
- Modality
- text+image->text+image
- Input modalities
- image, text
- Output modalities
- image, text
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | output: image |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Google AI Studio | 131,072 | — | — | — | — | — |
| 65,536 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.