Nano Banana
Nano Banana is the codename, later turned official brand, for Google's native image generation and editing models built into the Gemini ecosystem and developed by Google DeepMind. The original Nano Banana is Gemini 2.5 Flash Image, launched on August 26, 2025, and known for character consistency, multi-image fusion, and conversational natural-language editing. [1] [18] Before its reveal it competed anonymously as nano-banana on the LMArena Image Edit leaderboard, where it took the number one spot with the largest Elo score lead in Arena history, 171 points, after drawing more than 5 million community votes in two weeks. [2] On November 20, 2025, Google released a successor, Nano Banana Pro (Gemini 3 Pro Image), built on the Gemini 3 Pro reasoning model with 4K output, multilingual text rendering, and Google Search grounding. [3] Google has since extended the line with Nano Banana 2 (Gemini 3.1 Flash Image) on February 26, 2026, Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) on June 30, 2026, and Nano Banana 2.1 on October 6, 2026. As of November 2026 the original gemini-2.5-flash-image model is deprecated in the Gemini API, with a shutdown date of March 15, 2027. [19] [20]
The name first appeared in August 2025, when the anonymous nano-banana model started winning blind comparisons on LMArena for image editing. Google revealed the model's true identity on August 26, 2025, when it launched Gemini 2.5 Flash Image, the production version of the system that had been generating buzz for roughly two weeks. The nickname stuck and Google eventually adopted it as the official branding for the consumer product line. [1] [11]
Nano Banana Pro, the November 2025 upgrade, added higher-resolution output (up to 4K), improved multilingual text rendering, support for blending up to 14 reference images into a single composition, and tighter character consistency across up to five subjects. [1] Both models include invisible SynthID watermarks on every output. Images made in the Gemini app have also carried a visible watermark since the original model's launch; with the Pro model Google kept the visible Gemini sparkle for free and Google AI Pro users but removed it for Google AI Ultra subscribers and in Google AI Studio. [1] [26]
At the Nano Banana Pro launch, the Nano Banana family was positioned as Google's direct competitor to GPT Image 1, FLUX.2, and Ideogram 3.0 in the native multimodal AI image generation space, and it sat alongside Google's standalone text-to-image model Imagen 4 in the company's overall image stack. OpenAI has since released GPT Image 2 (April 21, 2026), and Google shut down the Imagen 4 models in the Gemini API on August 17, 2026, naming Nano Banana 2.1 as their replacement. [19] While Imagen specialized in pure generation tasks, Nano Banana is built into the Gemini conversational interface and is optimized for iterative editing, character consistency, and image-grounded reasoning.
Overview
| Attribute | Nano Banana (original) | Nano Banana Pro |
|---|---|---|
| Official model name | Gemini 2.5 Flash Image | Gemini 3 Pro Image |
| Developer | Google DeepMind | Google DeepMind |
| Public release | August 26, 2025 | November 20, 2025 |
| LMArena debut | August 12, 2025 (anonymous) | Not applicable |
| Underlying foundation | Gemini 2.5 Flash | Gemini 3 Pro |
| Maximum resolution | Standard (about 1K) | 1K, 2K, or 4K |
| Character consistency | Yes | Up to 5 characters |
| Multi-image input | Yes | Up to 14 objects per composition |
| Watermarking | SynthID (invisible), plus a visible watermark in the Gemini app | SynthID plus visible Gemini sparkle on free and Pro tiers |
| Available aspect ratios | 1:1, 16:9, 9:16, others | 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
| API price per image (standard) | $0.039 | $0.134 (lower resolutions) |
| API price per image (4K) | Not applicable | $0.24 |
| API access | Gemini API, Google AI Studio, Vertex AI | Gemini API, Google AI Studio, Vertex AI |
Background
Google had been building image generation capability into the Gemini product line throughout 2024 and early 2025, but the work was split across separate components. The Gemini app could call out to Imagen for text-to-image requests, and Gemini's vision tower could describe or analyze input images, but the two paths were not unified. That meant editing a generated image often required regenerating the whole picture from a new prompt, and the model could not reliably keep a character looking the same across multiple turns of a conversation.
In parallel, OpenAI shipped native GPT-4o image generation inside ChatGPT on March 25, 2025, and brought the model to its API as GPT Image 1 on April 23, 2025. [12] [22] The launch triggered the Studio Ghibli style transfer wave that swept social media for several weeks and pushed OpenAI's infrastructure to its limits. GPT Image 1's selling point was native multimodality: the same transformer that handled text also generated and edited images, which meant edits preserved context far better than pipeline-based systems. The bar for image generation shifted almost overnight, and Google's response had to clear it.
Why did nano-banana go viral on LMArena?
On or around August 12, 2025, a new entrant called nano-banana showed up in LMArena's Image Edit Arena. LMArena runs blind A/B tests where users vote on which of two anonymized models produced a better result for a given prompt. The new model started winning at an unusual rate, particularly on edits that required preserving the identity of a subject, like changing the background behind a person without altering their face or pose.
Within two weeks, the anonymous model attracted more than 5 million total community votes on LMArena, with more than 2.5 million votes cast for that model alone, the highest participation any model had recorded at the time. [2] Crucially, it took the number one spot in the Image Edit Arena with the largest Elo score lead in Arena history, 171 points. [2] LMArena CTO Wei-Lin Chiang later told Business Insider that traffic to the arena increased tenfold during that window and that monthly users had passed 3 million. Speculation about the model's origin spread quickly, with theories pointing to Google, Black Forest Labs, ByteDance, and several other groups, but no one confirmed anything until Google itself broke the silence.
The codename has an unusual origin that Google later documented. Naina Raisinghani, a product manager at Google DeepMind, named the model in the early hours before its anonymous LMArena submission. "We pushed the codename conversation until the last minute. So at 2:30 a.m., one of the PMs messaged me saying we needed to submit it, and I said, 'OK, how about something funny like "Nano Banana"?'" she recalled. [11] The name smushed together two of her own nicknames, "Naina Banana" and "Nano," and it also fit a Flash model. When the buzz outgrew the testing context, Google leaned into the branding rather than trying to replace it, adding banana emojis in the Gemini app and yellow run buttons in AI Studio. [11]
When was Nano Banana revealed as Gemini 2.5 Flash Image?
On August 26, 2025, Google publicly identified nano-banana as Gemini 2.5 Flash Image. The model launched the same day across the Gemini app, the Gemini API, Google AI Studio, and Vertex AI. [1] [4] LMArena posted the reveal on X with a banana emoji and confirmed that the anonymous model had been Gemini-2.5-Flash-Image-Preview by Google DeepMind. [10]
Gemini 2.5 Flash Image was priced at $30 per million output tokens, with each generated image counting as 1,290 tokens, which worked out to roughly $0.039 per image at the API level. [18] [15] That was cheap enough for high-volume use cases like e-commerce catalog generation, social media variants, and product mockups. Developers could call the model through the Gemini API directly or through Vertex AI for enterprise integrations, and OpenRouter and fal.ai added it to their hosting catalogs within days. [16]
Google's technical pitch for Gemini 2.5 Flash Image had four core features. It supported character consistency across turns, which Google framed as solving "a fundamental challenge in image generation": "maintaining the appearance of a character or object across multiple prompts and edits." [18] It could "understand and merge multiple input images" into a single composition. It accepted "targeted transformation and precise local edits with natural language," like "remove the trash can on the left" or "change the lighting to golden hour." And it inherited Gemini's world knowledge, which let it reason about what was actually in an image when deciding how to modify it. [18]
What is the difference between Nano Banana and Nano Banana Pro?
Google announced Gemini 3 Pro on November 18, 2025, as the next generation of its flagship reasoning model. Two days later, on November 20, the company released Nano Banana Pro, an image generation and editing system built directly on Gemini 3 Pro rather than on the lighter Flash model. [1] [3] The Pro version inherited the same naming convention as the original but routed image requests through a model with substantially more capacity for reasoning, planning, and language understanding.
What changed in Nano Banana Pro?
The headline upgrade was resolution. Nano Banana Pro produces output at 1K, 2K, or 4K, where the original was limited to roughly 1K. [1] In the Gemini API it supports ten aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9. [27] Google's model page also demonstrates reframing an existing image to cinematic ratios such as 1.85:1, 2.39:1, and 2.75:1 by prompt. [3]
Character consistency expanded from a single subject focus to maintaining the consistency and resemblance of up to five people across a scene, with each able to appear from different angles and distances while remaining recognizable. [1] Composition capacity grew to up to 14 input images per workflow, which allows users to assemble complex scenes by referencing many separate source pictures. [1] Google demonstrated this on launch with infographics that combined typography, photographic reference, and diagrammatic layout into a single output.
Text rendering improved significantly. Google called Nano Banana Pro "the best model for creating images with correctly rendered and legible text directly in the image," with support for long captions and multiple languages including Chinese, Japanese, Korean, and European scripts. [1] [3] The model can render long captions, paragraphs, calligraphy, and varied typography directly inside generated images, which makes it usable for posters, social media graphics, and translation-localized creative assets without a separate text overlay pass.
How does reasoning-grounded generation work?
The most important architectural change was that Nano Banana Pro inherits Gemini 3 Pro's reasoning capacity and "can also connect to Google Search's vast knowledge base" for real-time information. [1] That means a prompt like "create a chart of the top ten countries by population in 2025" can pull current data through Search, structure it, and render the chart with correct numbers and country names. Earlier image models could produce something that looked like a chart but contained hallucinated values; Nano Banana Pro can actually ground the content in retrievable facts.
This also extends to infographics and explainer diagrams, where the model can reason about the subject before composing the layout.
Capabilities
| Feature | Nano Banana (original) | Nano Banana Pro |
|---|---|---|
| Text-to-image | Yes | Yes |
| Image-to-image editing | Yes | Yes |
| Natural-language local edits | Yes | Yes, with finer control |
| Character consistency | Single subject | Up to 5 subjects |
| Multi-image fusion | Yes | Up to 14 input images |
| Camera angle and lighting controls | Limited | Wide-angle, panoramic, close-up, depth of field, day-to-night |
| Color grading | Basic | Full color palette manipulation |
| Native text rendering | Limited | Long captions, multiple languages, varied typography |
| Search-grounded generation | No | Yes, via Gemini 3 Pro and Google Search |
| Maximum resolution | About 1K | 4K |
| Aspect ratios | 1:1, 16:9, 9:16, several others | 10 ratios in the API, from 21:9 to 9:16 |
| Watermark | SynthID (invisible), plus a visible watermark in the Gemini app | SynthID plus visible Gemini sparkle on free and Pro tiers (removed on Ultra) |
Both models accept text prompts and reference images as input. Editing is conversational, so a user can ask for one change, then another, then another, and the model carries the context forward without losing the subject. Targeted edits include object removal, pose change, background swap, lighting shift, color grade, and style transfer. The Pro model's lighting controls extend to specific directional sources, day-to-night transitions, and depth of field adjustments that approximate real camera settings.
The documentation acknowledges some limitations. Masked editing, major lighting changes, and complex multi-image blends can occasionally produce artifacts, particularly when many constraints stack on a single prompt. The model tends to perform best when given a clear primary subject and one or two reference inputs rather than 14. [15]
Availability and pricing
| Surface | Original Nano Banana | Nano Banana Pro |
|---|---|---|
| Gemini app (free) | Yes, with daily quota | Limited free quota |
| Google AI Plus, Pro, Ultra | Yes, higher quotas | Yes, higher quotas |
| Search AI Mode | Yes (Create Images) | Yes ("Create Images Pro" with Thinking 3 Pro) |
| NotebookLM | Yes | Yes, globally for all users |
| Workspace (Slides, Vids) | Limited | Yes, with "Help me visualize" and "Beautify this slide" |
| Flow (filmmaking) | Limited | All paid plans |
| Mixboard | No | Yes |
| Google Ads | Yes | Yes, globally |
| Gemini API | $0.039 per image | $0.134 to $0.24 per image |
| Vertex AI | Yes | Yes (paid preview at launch) |
| Google AI Studio | Free testing | Free testing |
| Antigravity, Firebase, Stitch | Yes | Yes |
For the API, Nano Banana Pro pricing operates on three components: text and image input tokens at $2 per million, thinking output tokens at $12 per million, and image generation tokens that work out to roughly $0.134 per image at standard resolution and $0.24 per image at 4K, according to Google's Gemini API pricing page. [21] The original Nano Banana remained available alongside the Pro model for fast and inexpensive editing; as of November 2026 the gemini-2.5-flash-image model is deprecated, with a shutdown date of March 15, 2027 and Gemini 3.1 Flash-Lite Image named as its replacement. [19] [21]
Consumer tier handling differs from the API. At the Pro launch, free Gemini users received a limited Nano Banana Pro quota, after which the app reverted to the original Nano Banana; Google AI Plus, Pro and Ultra subscribers received higher quotas. [1] [7] Since February 26, 2026, Nano Banana 2 has replaced Nano Banana Pro across the Gemini app's Fast, Thinking and Pro models, with Google AI Pro and Ultra subscribers keeping access to Nano Banana Pro by regenerating an image. [20] Google AI Ultra subscribers get the highest quotas and, importantly, get the visible Gemini sparkle watermark removed from their output images, leaving only the invisible SynthID signal. [1] [7]
For enterprise, the model is available through Vertex AI with built-in SynthID watermarking, and Google Cloud said copyright indemnification would come at general availability. Google Cloud announced enterprise availability for Nano Banana Pro alongside the consumer launch in November 2025. [5]
How does SynthID watermarking work in Nano Banana?
Every image generated by either Nano Banana model carries an invisible SynthID watermark, the digital provenance signal developed by Google DeepMind. Google states that "all images created or edited with Gemini 2.5 Flash Image will include an invisible SynthID digital watermark, so they can be identified as AI-generated or edited." [1] SynthID embeds a pattern in the pixel data that survives many common transformations like cropping, color correction, and JPEG compression, and can be detected by a verifier even if the watermark itself is not visible to a human.
The Gemini app includes a SynthID verifier that lets users upload an image and check whether it was generated by a Google model. Google has positioned SynthID as part of its broader response to concerns about misinformation, deepfakes, and synthetic media, and it is now standard across Google's generative output, including Imagen, Veo video generation, and the Gemini text-to-music tools.
For Nano Banana Pro, the watermarking has two layers. The invisible SynthID signal is on every output regardless of subscription tier. The visible Gemini sparkle watermark appears on outputs from free and Google AI Pro accounts, but Google AI Ultra subscribers and the Google AI Studio developer tool can deliver images without the visible mark. [1] [3] The invisible SynthID layer is never removed.
This tiered approach has drawn some criticism. Removing the visible watermark on a paid tier makes it harder for casual viewers to tell a generated image apart from a real one at a glance, even if SynthID detection is still possible with the verifier. Critics have argued that the visible mark should be mandatory across all tiers for that reason. Google's position is that professional users producing client work need the option to deliver clean images, while the invisible SynthID layer preserves the underlying provenance signal.
How does Nano Banana compare to GPT Image 1, FLUX.2, and Ideogram?
The table below reflects the field at the Nano Banana Pro launch in late 2025. Several entries have since been superseded or retired, including by OpenAI's GPT Image 2 (April 21, 2026) and the Imagen 4 shutdown in the Gemini API (August 17, 2026). [19]
| Model | Developer | Type | Resolution | Text rendering | Watermark | API price per image |
|---|---|---|---|---|---|---|
| Nano Banana Pro | Google DeepMind | Native multimodal, reasoning-grounded | Up to 4K | Strong, multilingual | SynthID plus visible sparkle | $0.134 to $0.24 |
| Nano Banana (original) | Google DeepMind | Native multimodal | About 1K | Limited | SynthID | $0.039 |
| GPT Image 1 | OpenAI | Native multimodal | Up to 1536x1024 | Good | C2PA Content Credentials | About $0.02 to $0.19 (square images) [22] |
| FLUX.2 | Black Forest Labs | Diffusion transformer | Up to 4 megapixels [25] | Strong | Optional | Open weights and hosted tiers |
| Ideogram 3.0 | Ideogram | Diffusion | Up to 2K | Strongest in class on typography | Optional | Subscription tiers |
| Imagen 4 | Google DeepMind | Text-to-image | Up to 2K | Strong | SynthID | Retired in the Gemini API on August 17, 2026 [19] |
Direct comparisons published in late 2025 generally placed Nano Banana Pro at or near the top of the consumer-friendly category, especially for edits that required reasoning, text inside the image, or multi-image composition.
WIRED's February 2026 hands-on with the successor model, Nano Banana 2, found rougher edges: a prompt asking for a photorealistic image of the reviewer skiing "ripped and shirtless" produced a result he said "looks more like a bad Photoshop." [24]
Against GPT Image 1, Gemini 2.5 Flash Image was widely seen as more reliable at character consistency. GPT Image 1 launched first, in March 2025, and its viral moment was driven by stylistic creativity rather than identity preservation. When OpenAI's model was used to edit a specific person's portrait into a new setting, the face would often drift across iterations. Nano Banana made that the headline feature, and the Pro version made it stronger by extending the consistency guarantee across multiple subjects. [12]
FLUX.2 from Black Forest Labs remains a benchmark competitor with strong text rendering and an open-weights option that Nano Banana does not match. For users who need to run image generation on their own infrastructure or fine-tune the model on a private dataset, FLUX is generally the practical choice. Nano Banana is closed-source and is only available through Google's hosted endpoints.
Ideogram 3.0 remains the in-class leader for pure typography work, particularly stylized text, logos, and complex layouts that involve text as a primary design element. Nano Banana Pro narrowed that gap significantly with its long-paragraph rendering and multilingual support, but Ideogram still tends to win on typography-heavy creative briefs.
Reception
The initial LMArena buzz in August 2025 was the most extreme reaction any image model had received on that platform up to that point. More than 5 million votes in two weeks, a tenfold traffic increase, and 3 million monthly active users for an arena that had been a niche research tool meant that the broader AI community noticed the model before Google had even confirmed its existence. [2] By the time the reveal happened, the brand was already locked in.
The reveal-day coverage was generally positive. TechCrunch focused on the character consistency angle and the obvious framing as a direct counterpunch to GPT Image 1. [12] Coverage in the developer press emphasized the price, which at $0.039 per image was meaningfully lower than competitors and made high-volume use cases viable. [15]
Reception of Nano Banana Pro was more mixed. The headline capabilities were impressive: 4K output, multilingual long-text rendering, up to 14-image composition, and reasoning-grounded generation. The Verge ran a piece titled "Google's Nano Banana Pro generates excellent conspiracy fuel" that pointed at the obvious risk of a model that can produce convincing fake infographics, fake news layouts, and fake document scans. [13] Critics worried that the combination of legible text inside images plus Search-grounded reasoning created a tool well-suited for misinformation, regardless of the SynthID watermarking.
Other reviewers noted that the upgrade in quality was real and visible. Developer Simon Willison called Nano Banana Pro "the best available image generation model" in his hands-on writeup the day it launched. [23]
Within the broader Google ecosystem, the integration was the more important story. Nano Banana Pro shipped at launch or within weeks across the Gemini app, NotebookLM, Workspace (Slides and Vids), Search AI Mode, Mixboard, Flow, Google Ads, and the developer surfaces (Gemini API, Vertex AI, AI Studio, Antigravity, Firebase, Stitch). [7] [8] [9] That depth of distribution meant the model reached millions of users within days rather than waiting for individual product teams to wire it in over months. Adobe also announced an integration with Firefly and Photoshop on November 20, 2025, which gave Nano Banana Pro a direct path into professional creative workflows outside of Google's own surfaces. [14]
The original Nano Banana stayed available alongside the Pro version for cheap and fast edits. That dual-track approach mirrors how Google handles its Gemini text models, where Flash and Pro variants coexist with different cost and capability trade-offs. Through early 2026 the original Nano Banana was the everyday option and Pro was reserved for higher-stakes work that needed the resolution, the text, or the reasoning. [7] That changed on February 26, 2026, when Nano Banana 2 became the default image model in the Gemini app. [20]
Continue reading
- Gemini (language model)Gemini is a family of natively multimodal large language models developed by Google DeepMind, first announced on December 6, 2023, that can reason across text, images, audio, video, and code within a single…Mentioned 60 times above
- SynthIDSynthID is a family of digital watermarking technologies developed by Google DeepMind for marking and identifying content generated by generative AI systems.Mentioned 21 times above
- Google DeepMindGoogle DeepMind is an artificial intelligence research and model-development organization at Google.Mentioned 10 times above
- Gemini 3 ProGemini 3 Pro was the flagship preview model in Google DeepMind's Gemini 3 family of multimodal models, launched on November 18, 2025 as what Google called "our most intelligent model." It became the first…Mentioned 8 times above
- GPT Image 1GPT Image 1 (API identifier gpt-image-1) is a natively multimodal image generation model developed by OpenAI, integrated into ChatGPT on March 25, 2025, and released as a standalone API on April 23, 2025.Mentioned 8 times above
- Imagen 4Imagen 4 is the fourth-generation text-to-image model developed by Google DeepMind, announced on May 20, 2025, at Google I/O 2025.Mentioned 4 times above
More from See also
More to read
Topics:AI ModelsComputer VisionGenerative AIImage Generation
References
- ^1 ^2 ^3 ^4 ^5 ^6 ^7 ^8 ^9 ^10 ^11 ^12 ^13 ^14 ^15Google DeepMind. "Nano Banana Pro: Gemini 3 Pro Image model from Google DeepMind." The Keyword, November 20, 2025. blog.google/...nano-banana-pro
- ^1 ^2 ^3 ^4LMArena. "Nano-Banana (Gemini 2.5 Flash Image): Try it on LMArena." August 2025. news.lmarena.ai/nano-banana
- ^1 ^2 ^3 ^4 ^5Google DeepMind. "Gemini 3 Pro Image - Nano Banana Pro." DeepMind Models, November 2025. deepmind.google/...pro
- ^Google Cloud. "Use Gemini 2.5 Flash Image (nano banana) on Vertex AI." August 26, 2025. cloud.google.com/...i-2-5-flash-image-on-vertex-ai
- ^Google Cloud. "Announcing Nano Banana Pro for every builder and business." November 20, 2025. Archived copy: web.archive.org/...na-pro-available-for-enterprise
- Google. "Developers can build with Nano Banana Pro (Gemini 3 Pro Image)." November 20, 2025. blog.google/...gemini-3-pro-image-developers
- ^1 ^2 ^3 ^4Google. "Here's where you can use Nano Banana Pro." December 23, 2025. blog.google/...where-to-use-nano-banana-pro
- ^Google Workspace Blog. "November Workspace Drop: Nano Banana Pro in Slides, Vids, and the Gemini app." November 2025. workspace.google.com/...ro-in-slides-vids-and-more
- ^Google. "Gemini 3 Flash is rolling out globally in Google Search." December 17, 2025. blog.google/...google-ai-mode-update-gemini-3-flash
- ^LMArena. "Big Reveal: who was Nano Banana?" X (formerly Twitter), August 26, 2025. x.com/...1960342813599760516
- ^1 ^2 ^3Google. "How Nano Banana got its name." The Keyword, January 2026. blog.google/...how-nano-banana-got-its-name
- ^1 ^2 ^3TechCrunch. "Google Gemini's AI image model gets a 'bananas' upgrade." August 26, 2025. techcrunch.com/...age-model-gets-a-bananas-upgrade
- ^The Verge. "Google's Nano Banana Pro generates excellent conspiracy fuel." X, November 2025. x.com/...1991821660287320229
- ^Adobe Blog. "Create with unlimited generations using Google Gemini 3 (Nano Banana Pro) in Adobe Firefly." November 20, 2025. blog.adobe.com/...ano-banana-pro-firefly-photoshop
- ^1 ^2 ^3Google AI for Developers. "Gemini 2.5 Flash Image (Nano Banana) - Gemini API documentation." 2025. ai.google.dev/...gemini-2.5-flash-image
- ^fal.ai Blog. "Introducing Gemini 2.5 Flash Image Edit aka nano-banana." August 2025. blog.fal.ai/...-5-flash-image-edit-aka-nano-banana
- Wikipedia. "Nano Banana." Accessed 2026. en.wikipedia.org/...Nano_Banana
- ^1 ^2 ^3 ^4Google for Developers. "Introducing Gemini 2.5 Flash Image, our state-of-the-art image model." Google Developers Blog, August 26, 2025. developers.googleblog.com/...emini-2-5-flash-image
- ^1 ^2 ^3 ^4 ^5Google AI for Developers. "Gemini deprecations." Gemini API documentation, accessed November 2026. ai.google.dev/...deprecations
- ^1 ^2 ^3Google. "Nano Banana 2: Combining Pro capabilities with lightning-fast speed." The Keyword, February 26, 2026. blog.google/...nano-banana-2
- ^1 ^2Google AI for Developers. "Gemini Developer API pricing." Accessed November 2026. ai.google.dev/...pricing
- ^1 ^2OpenAI. "Introducing our latest image generation model in the API." April 23, 2025. openai.com/...image-generation-api
- ^Simon Willison. "Nano Banana Pro aka gemini-3-pro-image-preview is the best available image generation model." November 20, 2025. simonwillison.net/...nano-banana-pro
- ^Reece Rogers. "Hands-On With Nano Banana 2, the Latest Version of Google's AI Image Generator." WIRED, February 26, 2026. wired.com/...-banana-2-ai-image-generator-hands-on
- ^Black Forest Labs. "FLUX.2: Frontier Visual Intelligence." November 25, 2025. bfl.ai/...flux-2
- ^Google. "Nano Banana: Image editing in Google Gemini gets a major upgrade." The Keyword, August 26, 2025. blog.google/...updated-image-editing-model
- ^Google AI for Developers. "Image generation with Gemini." Gemini API documentation, accessed November 2026. ai.google.dev/...image-generation
Improve this article
Add missing citations, update stale details, or write a clearer explanation. Anyone can edit: changes go live when you publish, and every edit is checked by an editor.
7 revisions · v7 · 4,364 words · full history
Fact-checks are independent of edits: a reviewer re-verifies the article against its sources and stamps the date. How we verify
Research and drafting on this wiki are AI-assisted, under named human editorial standards. How AI is used here
Reviewer note: Independent fact-check of the full article against its cited sources (95 claims, 29 sources fetched); 12 material + 24 minor fixed
Cite this page: AI Wiki. "Nano Banana." aiwiki.ai, updated 28 Oct 2026, fact-checked 4 Nov 2026. CC BY 4.0. https://aiwiki.ai/wiki/nano_banana



