Google: Nano Banana Pro (Gemini 3 Pro Image Preview)
google/gemini-3-pro-image-preview
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to the OpenRouter catalog, google/gemini-3-pro-image-preview is a Google model listed under the name Nano Banana Pro (Gemini 3 Pro Image Preview). The catalog describes it as an image generation and editing model built on Gemini 3 Pro, accepting text and image inputs and producing text and image outputs over a context length listed as 65536 tokens. Reasoning is marked as mandatory in the catalog, which also lists parameters such as structured outputs, seed, temperature, and top_p. An independent model card was not available in this source pack, so these details should be treated as catalog-reported.[1]
Strengths
- Handles multimodal input and output, generating and editing images alongside text within a single request.[1]
- The catalog claims improved multimodal reasoning and real-world grounding relative to the earlier Nano Banana model.[1]
- Listed with practical generation controls including seed, structured outputs, and an always-on reasoning mode.[1]
Limitations
- All evidence comes from the OpenRouter catalog only; no independent model card or primary documentation was in this pack, so claims need workload validation.[1]
- The identifier carries preview status and the catalog provides no knowledge cutoff or expiration date, leaving stability and freshness unclear.[1]
- Reasoning is listed as mandatory with no supported effort levels, so it cannot be disabled, and license terms are not reported.[1]
Where to use it
- Worth evaluating for image generation and editing pipelines that combine prompts and reference images in one call.[1]
- Plausibly suited to design and marketing asset drafts, an area where the catalog records Design Arena leaderboard entries.[1]
- Consider for applications needing machine-readable text responses alongside imagery, given the listed structured output support.[1]
Sources
- [1] OpenRouter catalog · Google: Nano Banana Pro (Gemini 3 Pro Image Preview)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-preview
- Canonical ID
- google/gemini-3-pro-image-preview-20251120
- Creator
- Added to OpenRouter
- 20.11.2025
- Context length
- 65,536
- 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 |
| 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
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | models · graphicdesignwin rate 65.8% · rank 5 | 1,251Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · imagewin rate 62.1% · rank 5 | 1,226Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · logowin rate 61% · rank 6 | 1,241Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · imageeditingwin rate 66% · rank 3 | 1,227Elo | —Not rated | 13.11.2026 |
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 | 65,536 | — | — | — | — | — |
| Google AI Studio | 65,536 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.