Primary use stated or inferred cautiously from official documentation.
G
GOOGLE / gemini-nano-banana-2.1
Gemini Nano Banana 2.1
Google model for image generation and conversational editing, generally available since October 6, 2026. It replaces Nano Banana 2 and should not be confused with Nano Banana Pro. It accepts text, images, video and PDF as context; it produces images and text, not video or audio. Google reports improvements in visuals, instruction following, text rendering and consistency across edits.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | gemini-nano-banana-2.1 |
|---|---|
| Model type | Image |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 06 OCT 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · Video · PDF |
| Exit | Image · Text |
| Context window | 131,072 input tokens |
| maximum output | 32,768 tokens; 1K, 2K and 4K images |
| Reasoning | minimal, medium, high |
| Published tools | Image generation · Image editing · Web and image search |
| Structured Outings | No |
| Batch processing | Sí |
| Prompt cache | No |
| Fine-tuning | Not published |
| Verified platforms | Gemini API · Google AI Studio |
Create illustrations, infographics and visual variants from references. Supports up to fourteen reference images, with consistency for up to four characters and fidelity for up to ten objects. Offers 1K, 2K and 4K resolutions, defaulting to 1K, and panoramic ratios of 1:4, 4:1, 1:8 and 8:1. Generation can be grounded with web and image search.
The limits of 131,072 input and 32,768 output tokens are not a quality guarantee. Function calling, structured outputs, prompt caching and Live API are not supported. Thinking accepts minimal, medium and high; medium is the default. Review text, identities, composition and reference rights before publishing. Effective availability depends on your account quotas.
03 / CAPABILITIES
What it can do
Orientation
Create illustrations, infographics and visual variants from references. Supports up to fourteen reference images, with consistency for up to four characters and fidelity for up to ten objects. Offers 1K, 2K and 4K resolutions, defaulting to 1K, and panoramic ratios of 1:4, 4:1, 1:8 and 8:1. Generation can be grounded with web and image search.
Context
131,072 input tokens · 32,768 tokens; 1K, 2K and 4K images
Tools and integration
Image generation · Image editing · Web and image search
Access
Gemini API and Google AI Studio
Input modalities
TextImageVideoPDF
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 1,50 USD / 1 M tokens | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 0.0336 / 0.0504 / 0.113 USD per 1K / 2K / 4K image | May include reasoning tokens |
| Batch input | 0.75 USD / 1M tokens | Asynchronous processing |
| Batch output | 0.0168 / 0.0252 / 0.0567 USD per 1K / 2K / 4K image | Asynchronous processing |
Standard rates in USD per million tokens: input 1.50, output text and thinking 7.50, output images 30. Per-image amounts depend on resolution and exclude input, text and searches. Batch halves these rates; Google lists 0.0567 USD per 4K image in Batch. Searches share 5,000 free monthly requests with Gemini 3.x, then cost 14 USD per thousand queries. There is no free API tier. Numeric output fields are left empty to avoid mixing text and images.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
We have not verified published numerical scores for this version; announced improvements are not a comparable benchmark. We do not inherit results from Nano Banana 2 or Pro. Inferama’s image suite can assess instructions, text, references and edits using real artifacts, but has not been run on this release. For comparisons, match resolution, references, thinking level, attempt count, latency and total cost per usable image.
i No verified scores for Nano Banana 2.1; Inferama evaluation pending.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Gemini Nano Banana 2.1
Version added to Inferama's verified catalog.
07 / SOURCES