# Nano Banana 3 Flash (preview)

> Newer Gemini 3.1 image-gen, preview tier. Same edit-mode + tier pricing as stable; sharper output. The migration target for nano-banana, which Google retires 2026-10-20 — identical price.

Human version: https://kymaapi.com/models/nano-banana-3-flash
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `nano-banana-3-flash` — pass this as `model` in the request body
- **Creator**: Google
- **Released**: 2026-02-26
- **Price**: $0.046 / image

## Call it

```bash
curl https://kymaapi.com/v1/images/generations \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nano-banana-3-flash", "prompt": "..."}'
```

## Positioning

This is a preview-tier image generation and editing model from Google, built for developers who want the latest Gemini 3.1 architecture with faster inference and sharper output. Reach for it when you need cost-effective, high-speed image synthesis or prompt-driven edits in production workflows.

## About

Nano Banana 3 Flash is a preview release of Google’s Gemini 3.1 image generation model. It accepts text prompts and reference images, then outputs generated or modified images. The model is optimized for speed and sits in the cheap cost tier while delivering frontier-tier visual quality.

On Kyma, the model runs through an OpenAI-compatible endpoint with automatic failover across serving paths. Prompt caching is enabled, so repeated prompt prefixes are billed at 10% of the standard input rate. Every response returns the exact cost in the usage.cost field and identifies the executed model via the X-Kyma-Model header.

This is a preview build, so output consistency may shift as Google iterates. It does not support structured JSON outputs or reasoning traces, and it is strictly an image-to-image or text-to-image model. Google plans to retire the older nano-banana model in October 2026, making this the direct migration path.

## Use cases

- **Generate marketing assets** — Produce high-resolution product and campaign visuals from text prompts at low cost.
- **Edit reference images** — Modify existing photos using text instructions while preserving layout and composition.
- **Prototype UI mockups** — Quickly render interface concepts and layout variations for early-stage design reviews.
- **Batch image synthesis** — Run large-scale generation jobs where speed and cheap-tier pricing matter most.

## Not ideal for

Do not use this model if you require guaranteed output stability, structured data extraction, or multi-step reasoning alongside image generation.

## Pick something else when

- You need guaranteed production stability → `imagen-4`
- You need vector graphic generation → `recraft-v4-vector`
- You need photorealistic portrait editing → `flux-2-pro`
- You need the highest possible resolution → `imagen-4-ultra`

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by Google: https://kymaapi.com/models?q=Google