Google Nano Banana 2 Lite
Google's fastest, most cost-efficient Nano Banana model — 1K images in ~4 seconds for high-volume workflows.
Nano Banana 2 Lite is a cloud image-generation model from Google. It generates images from a text prompt, and can take reference images to guide style or composition (image-to-image). It outputs up to 1K across 14 aspect ratios. Images can be saved as PNG, JPEG, and WebP. It runs through Runware, Replicate, OpenRouter, and Google using your own API key, from about $0.0336 per image.
- Released
- 3 months ago (Jun 2026)
- Pricing
- $0.0336 per image
- Max resolution
- 1K
- Aspect ratios
- 1:1, 16:9, 9:16 +11 more
- Image-to-image
- Up to 14 reference images
- Output formats
- PNG, JPEG, WebP
Examples
Generated with Nano Banana 2 Lite via Runware. The same three prompts run against every model in the catalog, first result kept, so the only thing that changes between two models’ tiles is the model.
Materials, reflections, macro detail
Skin texture, lighting, shallow depth of field
Text rendering, layout, flat colour
Google and Google DeepMind build the Gemini family of multimodal models, the Imagen and Nano Banana image models, the Lyria music models, and the Veo video models.
deepmind.google ↗Google's most capable Flash model, with clear gains over 3.7 Flash in software engineering, agentic tasks, and multi-step reasoning, plus vision and a 1M-token context window.
Google's newest Flash workhorse, a more capable successor to 3.6 Flash with stronger software engineering, better document comprehension and more disciplined tool use, at half the price per token.
Google's most efficient multimodal Flash model: an updated reasoning stack with stronger coding and computer-use quality, at the same speed and scale as the rest of the Flash line.
Google's most capable multimodal model with deep reasoning and 1M token context.
Ultra-fast image generation model optimised for speed and creative output.
Google's original Nano Banana, the Gemini 2.5 image model for fast generation and conversational editing that holds a subject's likeness across successive edits.
Most AI image models are great at art and terrible at keeping your actual product. Five that aren't, ranked on fidelity over beauty.
A phone, a kitchen window, four AI tools, sixty-three cents in API credits. Forty-two minutes to a six-shot product gallery.
Forty-seven minutes. Three dollars and seventy-three cents. Every prompt, every cost, one API — and the finished ad, embedded.