Google launches Gemini Omni Flash and Nano Banana 2 Lite for video and image generation

Google released two new generative AI models on June 30, 2026: Gemini Omni Flash, a multimodal video generation and editing model priced at $0.10 per second of video output, and Nano Banana 2 Lite (gemini-3.1-flash-lite-image), the company's fastest image model at $0.034 per 1,000 images. Both are available now in Google AI Studio and the Gemini API.

What's new

Nano Banana 2 Lite (model ID: gemini-3.1-flash-lite-image):

• Text-to-image generation in 4 seconds
• $0.034 per 1,000 images at 1K resolution
• Strong prompt adherence, character consistency, and legible in-image text rendering
• Positioned as the recommended replacement for the original Nano Banana (gemini-2.5-flash-image)
• Available in Google AI Studio, Gemini API, and consumer surfaces including AI Mode in Search, Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads

Gemini Omni Flash (model ID: gemini-omni-flash-preview):

• Multimodal model combining Gemini reasoning with video generation and editing
• $0.10 per second of video output
• Generates up to 10-second videos; accepts video reference inputs up to 3 seconds
• Conversational editing: refine and edit videos using natural language commands
• Text and action synchronization; leverages real-world knowledge for narrative generation
• Available in Google AI Studio, Gemini API, Gemini app, and Google Flow
• Limitations: character consistency with scene changes has known issues; audio references and scene extension not yet supported

Both models include SynthID watermarking for AI-generated content verification via Gemini app, Chrome, and Search.

The two models integrate via the Interactions API, enabling sequential workflows: generate an image with Nano Banana 2 Lite, then animate it into a video with Gemini Omni Flash, with support for up to three sequential edits per pipeline.

Context

Nano Banana 2 Lite is the second generation of Google's fast image model line. The original Nano Banana (gemini-2.5-flash-image) debuted earlier this year. The new model achieves higher throughput at a lower price point, targeting developers who need rapid iteration at scale.

Gemini Omni Flash enters the video generation API market with a model that offers both generation and natural-language editing in a single surface. Current competitors in the developer video API space include Runway Gen-4 and Pika 2.1, neither of which natively combines video generation with conversational editing at the API level.

Why it matters

The combined launch extends Google's coverage across both image and video generation at competitive prices. At $0.034 per 1,000 images, Nano Banana 2 Lite undercuts many competitors in the high-throughput image tier while delivering 4-second outputs. Gemini Omni Flash brings conversational video creation directly into the Gemini API ecosystem with clear pricing.

The Interactions API integration enabling image-to-video pipelines is the more structurally interesting development: developers can chain image generation and video animation in a single API surface, reducing friction in mixed-media production workflows. This positions Google's generative media suite as a coordinated platform rather than a collection of standalone model endpoints.