---
title: "Nano Banana API — All variants, pricing, code samples | RunAPI"
url: "https://runapi.ai/models/nano-banana.md"
canonical: "https://runapi.ai/models/nano-banana.md"
locale: "en"
model: "Nano Banana"
provider: "Google"
modality: "image"
variant_count: 4
price_from_cents: 4
---

# Nano Banana

Fast text-to-image with accurate in-image text rendering and multi-character consistency.

**Provider:** Google
**Modality:** Image
**Catalog:** 4 variants

Nano Banana is Google's fast image generation model optimized for accurate text rendering within images and consistent multi-character scenes. It delivers rapid results without sacrificing prompt fidelity.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| nano-banana | `nano-banana` | $0.040 | call | https://runapi.ai/models/nano-banana/nano-banana.md |
| nano-banana-2 | `2` | $0.160 | call | https://runapi.ai/models/nano-banana/2.md |
| nano-banana-edit | `edit` | $0.040 | call | https://runapi.ai/models/nano-banana/edit.md |
| nano-banana-pro | `pro` | $0.180 | call | https://runapi.ai/models/nano-banana/pro.md |


## Install

```sh
npm install @runapi.ai/nano-banana
# or
gem install runapi-nano_banana
```

## Quickstart

```sh
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "nano-banana", "prompt": "..." }'
```

## Context

Nano Banana is Google's image model embedded in Gemini, purpose-built for fast generation with in-image text accuracy. Through RunAPI, all Nano Banana variants share a single key.

## FAQ

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.

### Is there a free tier?

New accounts get free first calls on every model. After that, pay per call.

### Do you stream results?

Where streaming is available, RunAPI streams end-to-end.

### How are failures billed?

Failed generations are not charged.

### Are outputs cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I use commercially?

Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.

### What about rate limits?

Per-key rate limits scale with usage tier. See pricing page for current limits.

### Where can I report issues?

Open an issue on the public GitHub repo or email support.