Nano Banana 2 Lite Edit Developer API by Google
Google's fastest and most cost-efficient Nano Banana image model for editing, applying natural-language edits and multi-image composition to up to 14 reference images with low latency.
Google Nano Banana 2 Lite — Edit Developer
Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image, gemini-3.1-flash-lite-image) is Google's fastest and most cost-efficient image model in the Nano Banana family. This variant is driven by one or more input images plus a natural-language prompt, applying conversational edits and multi-image composition with the same low latency that defines the Lite tier.
It shares the underlying model with the text-to-image variant — the difference is the input: you supply up to 14 reference images and describe the change you want, and the model edits, combines, or transforms them accordingly. It replaces the original Nano Banana (Gemini 2.5 Flash Image) with improved visual quality, stronger character consistency, and more legible in-image text, all while being faster and cheaper.
🌟 Why it stands out
- Natural-language editing — Modify images by describing the change in plain words — no masking, layering, or manual tools required.
- Multi-image composition — Accepts up to 14 input images to blend subjects, transfer styles, or assemble scenes from multiple references.
- Strong character consistency — Preserves character identities and object fidelity across edits, so subjects stay recognizable through repeated changes.
- Legible in-image text — Renders and localizes readable text directly within edited images for quick captioning and design tweaks.
- World knowledge — Understands scene structure and real-world context to keep edits coherent and plausible.
- Fast and cost-efficient — The budget-friendly member of the Nano Banana family, built for high-volume editing at scale. (Editing has slightly higher latency than pure text-to-image generation.)
⚙️ How to use
- Input: 1–14 reference image URLs + a text prompt
- Output: edited image (JPEG/PNG/WEBP), delivered as a URL (or BASE64 via the API)
- Resolution:
1k - Aspect ratios:
auto,1:1,3:2,2:3,3:4,4:3,4:5,5:4,9:16,16:9,21:9,4:1,1:4,8:1,1:8 - Thinking level:
default,high, orminimal— controls how much internal reasoning the model performs before editing. Higher levels can improve quality on complex tasks at the cost of latency;minimalmaximizes speed. - Supports style transfer, relighting, background replacement, object modification, and multi-image merging
- Works with natural prompts such as:
- "Replace the cloudy sky with a clear sunset."
- "Combine these two product shots into a single lifestyle scene."
- "Turn the model's outfit into a formal business suit and add soft studio lighting."
💰 Pricing
Pricing is a simple flat fee per generated 1k image. There is a single SKU and the total scales linearly with the number of images returned.
| SKU | Description | Unit Price |
|---|---|---|
sku_1k | 1k image | $0.04 |
Pricing Formula
cost = sku_1k × num_images
num_images— number of images generated by the request (default1). The number of input reference images does not affect the price.
Examples
| Images returned | Calculation | Total |
|---|---|---|
| 1 | $0.04 × 1 | $0.04 |
| 4 | $0.04 × 4 | $0.16 |
| 10 | $0.04 × 10 | $0.40 |
For the exact pricing configuration, see models/google/banana/price/google-nano-banana-2-lite-edit.json.
💡 Best Use Cases
- Marketing & branding — Update campaign visuals without reshooting.
- Virtual try-on & e-commerce — Swap outfits, backgrounds, or products across large catalogs at scale.
- Product photography — Adjust materials, lighting, or layout instantly.
- Social media & content creation — Generate many variations of an image with minimal effort.
- Compositing & concept art — Merge multiple references into cohesive scenes for storyboards and design exploration.
🔒 Content Authenticity
Edited images include C2PA content credentials and an imperceptible SynthID watermark by default, so outputs can be identified as AI-generated.
⚠️ Limitations
Optimized for speed and cost, this model may struggle with small faces, accurate spelling, and very fine details. Advanced edits, major lighting transformations, and image blending can occasionally produce unnatural results, visual artifacts, or disjointed scenes — for those cases, consider a higher-tier Nano Banana model.
📝 Notes
Please ensure your prompts comply with Google's Safety Guidelines. If an error occurs, review your prompt and input images for restricted content, adjust them, and try again.
🔗 Related Models
- Nano Banana 2 Lite — Text-to-Image — The same model driven by a text prompt only.
- Nano Banana Pro — Edit — Higher-fidelity editing tier for premium production.
