The model also expands creative controls. Users can adjust elements such as camera angle, focus, lighting, texture, color and style, and can combine multiple images into a single composition. Google also says the model improves text rendering for outputs such as posters, invitations, logos, comics, diagrams and infographics.
Nano Banana 2.1 supports up to 14 reference images at once and can track as many as four characters and 10 objects. It can generate images at up to 4K resolution and supports aspect ratios as wide as 8:1.
The model also adds more control over how much reasoning it uses before producing an image. Developers can set the model’s thinking level from minimal to high and can enable grounding through Google Search and Google Image Search before generation.
Google says Nano Banana 2.1 outperformed both Nano Banana 2 and Nano Banana Pro in internal preference testing. The new model scored 1,050 ELO points, compared with 990 for Nano Banana 2 and 935 for Nano Banana Pro.
The pricing is also lower than the previous generation. Through Google’s developer API, a standard 1K image costs $0.0336, compared with $0.067 for Nano Banana 2. A 4K image costs $0.0756, down from $0.151.
Batch processing receives an additional 50% discount. At the standard 1K rate, generating 1,000 images would cost about $33.60, compared with roughly $67 using Nano Banana 2.
Nano Banana became one of Google’s more visible consumer AI products after users began creating collectible-style figurine images from selfies. The original model helped push Gemini to the top of major app-store rankings in September 2025.
Google followed with Nano Banana 2 in February, adding stronger real-world grounding through Google Search. That model was built on Gemini 3.1 Flash Image.
Nano Banana 2.1 builds on that release with a heavier focus on editing quality and consistency. Users can maintain a character’s appearance across generated images, preserve objects through repeated changes and apply more localized edits without reworking the full scene.
The broader rollout also gives Google a single image model across consumer, advertising and developer products. For developers in particular, the combination of lower API pricing, adjustable reasoning and search grounding makes Nano Banana 2.1 a cheaper and more configurable option than its predecessor.
This analysis is based on reporting from Yahoo Tech.
Image courtesy of Google.
This article was generated with AI assistance and reviewed for accuracy and quality.
