# gemini-nano-banana-2.1 — API, Pricing & Image Tokens | Vivgrid

> Source: https://vivgrid.com/docs/models/gemini-nano-banana-2.1

gemini-nano-banana-2.1 (Nano Banana 2.1) on Vivgrid: Google's latest image generation and editing model, with a 131K-token context window, text, image and video input, and per-image token pricing.

`gemini-nano-banana-2.1`, also known as **Nano Banana 2.1**, is Google's image model for prompt-driven generation, multi-turn editing, and visual design workflows, succeeding [gemini-3.1-flash-image](/docs/models/gemini-3.1-flash-image) (Nano Banana 2). It takes text, image, and video input, supports thinking, and returns images alongside text — with image output at half the per-token price of Nano Banana 2.

On Vivgrid, `gemini-nano-banana-2.1` runs as a globally centralized model reachable through the same OpenAI-compatible endpoint and unified key as every other model in the catalog.

## Specifications

| Field | Value |
| --- | --- |
| Provider | Google |
| Model ID | `gemini-nano-banana-2.1` |
| Best for | Image generation |
| Context window | 131,072 tokens |
| Max output | 32,768 tokens |
| Modalities | Text, Image, Video |
| Tool / function calling | No |
| Knowledge cutoff | — |
| Acceleration | Global (centralized) |

## Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

| Input | Cached input | Output (text) | Output (image) |
| --- | --- | --- | --- |
| $1.50 | — | $7.50 | $30.00 |


## Image token conversion

Images are billed as tokens, so the per-image cost follows the resolution you ask for:

| Item              | Tokens | Cost per image |
| ----------------- | ------ | -------------- |
| Output image (1K) | 1,120  | \$0.0336       |
| Output image (2K) | 1,680  | \$0.0504       |
| Output image (4K) | 2,520  | \$0.0756       |

Text, image, and video input are all billed at \$1.50 per 1M tokens. Text and thinking tokens are billed at the text output rate of \$7.50 per 1M tokens. The model does not support context caching, so there is no cached-input rate.

## API surfaces

`gemini-nano-banana-2.1` is served on `/images/generations`, behind the same API key as the rest of the catalog.

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `gemini-nano-banana-2.1` directly.

```bash
curl https://api.vivgrid.com/v1/images/generations \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-nano-banana-2.1",
    "prompt": "A cozy reading nook with plants and warm light",
    "size": "1024x1024"
  }'
```


## Ideal use cases

- High-volume image generation pipelines
- Conversational, multi-turn image editing
- Product, marketing, and social-media creative from reference images or video
- Visual design workflows that need an image model at a mainstream price point

## Related models

- [gemini-3.1-flash-image](/docs/models/gemini-3.1-flash-image) — the prior Nano Banana 2 release
- [gemini-3-pro-image](/docs/models/gemini-3-pro-image) — Nano Banana Pro, Google's highest-quality image generation and editing
- [gpt-image-2.5-flare](/docs/models/gpt-image-2.5-flare) — OpenAI's gpt-image-2.5 image generation model