Back to feed
News Story
APriority77
Google DeepMind
3 sources

Start building with Nano Banana 2 Lite and Gemini Omni Flash

Original

This article announces that Nano Banana 2 Lite and Gemini Omni Flash are now available for developers to start building applications, highlighting new tools for development.

SynthePulse Insight · AI deep readingMembers

Google Unveils Nano Banana 2 Lite and Gemini Omni Flash: Faster, Cheaper Image Generation and First Video Generation API

Version 1 · 3 sources

Google has released two new generative AI models: Nano Banana 2 Lite for fast image generation and Gemini Omni Flash, which brings video generation and editing to the API for the first time. Together, they enable end-to-end multimedia applications, but the video model currently has length and feature limitations.

  • Nano Banana 2 Lite generates images in just 4 seconds, costing $0.034 per 1K-resolution image, cheaper than Nano Banana 2 ($0.067) and Pro ($0.134).
  • Gemini Omni Flash offers video generation and editing via API at $0.10 per second, matching Veo 3.1 Fast, but currently only supports 10-second clips.
  • Google recommends chaining the two models: first generate an image with Nano Banana 2 Lite, then animate it into a video with Gemini Omni Flash.
Open section navigationNano Banana 2 Lite: Speed and Cost Advantages

Nano Banana 2 Lite: Speed and Cost Advantages

Google released Nano Banana 2 Lite on June 30, 2026, positioning it for rapid ideation and high-throughput development pipelines. According to Google, the model generates images in just 4 seconds, with a cost of $0.034 per 1K-resolution image, significantly lower than Nano Banana 2's $0.067 and Nano Banana Pro's $0.134. The model identifier in the API is gemini-3.1-flash-lite-image.

Despite its speed, Google says Nano Banana 2 Lite reliably follows prompts, maintains character consistency, and generates readable text. The model has replaced the original Nano Banana (based on Gemini 2.5), which is now considered a 'legacy model.' Nano Banana 2 Lite is integrated into Google's consumer products, including AI Mode, the Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads.

TechCrunch reports the model is 'significantly faster and more affordable,' noting a cost of $0.034 per 1,000 images (likely a typo, should be per image). Google positions Nano Banana 2 as an 'all-rounder,' while Pro targets complex professional use cases with the strongest control and advanced reasoning.

Free for now

Read the full analysis

3 more sections of analysis, plus the full takeaway

Loading

Credibility boundary

This report is based on Google's official blog and reports from two tech outlets. Key data such as pricing, speed, and feature limitations come from Google's statements but have not been independently verified. TechCrunch's '$0.034 per 1,000 images' contradicts The Decoder's '$0.034 per image,' likely a typo, and is noted as a source claim.

Sources for this version

  1. Start building with Nano Banana 2 Lite and Gemini Omni FlashGoogle DeepMind
  2. Google launches Nano Banana 2 Lite for fast AI images and Gemini Omni Flash for video via APITHE DECODER
  3. Google introduces a faster, cheaper image generator with Nano Banana 2 LiteTechCrunch AI

Primary report

Google DeepMind

Primary source

Same-event coverage

Also covered by 2 sources

TechCrunch AIT3Google introduces a faster, cheaper image generator with Nano Banana 2 LiteOriginalTHE DECODERT2Google launches Nano Banana 2 Lite for fast AI images and Gemini Omni Flash for video via APIOriginal