Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) is the fastest, most cost-efficient image model in the Nano Banana family, generating and editing 1K images with reliable prompt adherence, strong character consistency, and legible in-image text for high-volume production workloads.
import { generateText } from 'ai'
const result = await generateText({ model: 'google/gemini-3.1-flash-lite-image', prompt: 'Render a picture of a red balloon.',});Playground
Try out Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) by Google. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)
Your generated image will appear here
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
Google | 66K | 0.4s | $0.25/M | $1.50/M | Read:$0.03/M Write:— | $14/K + input costs | — | +3 | 06/30/2026 | |||
 Google Vertex AI | 66K | 0.4s | $0.25/M | $1.50/M | Read:$0.03/M Write:— | $14/K + input costs | — | +3 | 06/30/2026 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Google
| Model |
|---|
| 1M | 2.3s | 202tps | $1.50/M | $9.00/M | Read:$0.15/M Write:— | $14.00/K + input costs | — | +4 | | 05/19/2026 | |||
| 1M | 0.4s | 246tps | $0.25/M | $1.50/M | Read:$0.03/M Write:— | $14.00/K + input costs | — | +4 | | 03/03/2026 | |||
| 1M | 4.2s | 105tps | $2.00/M | $12.00/M | Read: $0.2/M Write: — | $14.00/K + input costs | — | +4 | | 02/19/2026 | |||
| 1M | 0.8s | 166tps | $0.50/M | $3.00/M | Read: $0.05/M Write: — | $14.00/K + input costs | — | +4 | | 12/17/2025 | |||
| 1M | 0.4s | 242tps | $0.10/M | $0.40/M | Read:$0.01/M Write:— | $35.00/K + input costs | — | +4 | | 06/17/2025 | |||
| 1M | 0.4s | 194tps | $0.30/M | $2.50/M | Read:$0.03/M Write:— | $35.00/K + input costs | — | +4 | | 03/20/2025 |
About Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)
Google released Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) on June 30, 2026 as the fastest, most cost-efficient image model in the Nano Banana family. Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) is built for high-throughput pipelines where teams generate thousands of images and iterate quickly, keeping per-image cost low enough for near-real-time and high-volume workflows.
Despite the speed focus, Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) retains the traits the Nano Banana family is known for: reliable prompt adherence, strong character consistency, and legible in-image text rendering. Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) handles text-to-image generation, prompt-based editing, and multi-image composition through a single multimodal interface, so a generation pipeline and an editing pipeline can share one model.
The main tradeoff is resolution. Output is capped at 1K, while other models in the family generate at 2K and 4K. Google positions the lineup in three tiers: Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) for speed and scale, Gemini 3.1 Flash Image as the generalist, and Gemini 3 Pro Image for complex professional work. Google also recommends Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) as the upgrade path from the original Nano Banana, google/gemini-2.5-flash-image, citing better quality, faster generation, and lower cost.
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) accepts prompts within a context window of 65.5K tokens and returns text and images in the same response. Every generated image carries an invisible SynthID watermark for downstream identification of AI-generated content.
What To Consider When Choosing a Provider
- Configuration: Output resolution is capped at 1K; other models in the family generate at 2K and 4K. This is a multimodal model: call Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) with
generateTextorstreamTextand setresponseModalities: ['TEXT', 'IMAGE']inproviderOptions.googleto receive image output. Google notes that Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) can struggle with small faces, fine text detail, and complex masked edits, so route those jobs to a higher tier in the family. - Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)
Best For
- High-Volume Image Pipelines: Catalog imagery, thumbnails, and previews generated at scale where per-image cost dominates
- Rapid Creative Iteration: Fast generation loops that let users explore many variations before a final render
- Interactive Product Features: Low-latency image creation inside user-facing apps and tools
- Cost-Sensitive Editing Workflows: Prompt-based edits and multi-image composition at the lowest cost in the family
- Readable In-Image Text: Marketing cards, banners, and simple graphics that need legible rendered text
Consider Alternatives When
- Higher Resolution Required: 2K and 4K output need
google/gemini-3.1-flash-imageorgoogle/gemini-3-pro-image - Complex Professional Compositing: Fine-detail work and heavy multi-image blending land better on
google/gemini-3-pro-image - Video Input or Search Grounding:
google/gemini-3.1-flash-imageadds video-to-image and Google Image Search grounding - Text-Only Workloads: A text model like
google/gemini-3.1-flash-liteavoids per-image billing entirely - Video Output Required: Generated clips need the Veo model family rather than still images
Conclusion
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) makes image generation cheap and fast enough to treat as a high-volume primitive rather than a premium call. Keep Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) on the hot path for generation, iteration, and routine edits, and step up to Gemini 3.1 Flash Image or Gemini 3 Pro Image when a job needs higher resolution or heavier compositing.