> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bytespike.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Nano Banana 2

> Latest Nano Banana iteration — sharper in-image text rendering and improved hand / face anatomy.

**Vendor:** Google
**Model ID:** `nano-banana-v2`
**Capability:** 2048² · photorealism · sharp text rendering · improved anatomy
**Pricing:** per image, photoreal flagship tier ([live rate](https://bytespike.ai/pricing#image))

Nano Banana 2 is the current iteration of Google's photoreal family.
The two areas where it visibly improves over Pro: text rendering
inside the image (book covers, signage, screen content) and the
notorious anatomy edge cases (hand counts, face proportion at small
scale). For pure material / lighting fidelity, Pro and 2 are
comparable; for any brief that involves *legible* in-image text or
human subjects, 2 is the safer pick.

## Request

```bash theme={null}
curl https://llm.bytespike.ai/v1/images/generations \
  -H "x-api-key: $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "nano-banana-v2",
    "prompt": "A cafe storefront with a chalk-board menu reading PASTEL DE NATA and AMERICANO",
    "size": "2048x2048"
  }'
```

### Body parameters

| Field          | Type    | Required | Default      | Notes                                                          |
| -------------- | ------- | -------- | ------------ | -------------------------------------------------------------- |
| `model`        | string  | yes      | —            | `nano-banana-v2`                                               |
| `prompt`       | string  | yes      | —            | English-tuned.                                                 |
| `size`         | string  | no       | `2048x2048`  | Supported: `1024x1024`, `2048x2048`, `2048x1536`, `1536x2048`. |
| `n`            | integer | no       | 1            | 1–2 images.                                                    |
| `seed`         | integer | no       | —            | Reproducibility.                                               |
| `aspect_ratio` | string  | no       | —            | `1:1` / `9:16` / `16:9` / `4:3` / `3:4`.                       |
| `quality`      | string  | no       | `"standard"` | `"standard"` / `"hd"`.                                         |

## Response

```json theme={null}
{
  "created": 1715174400,
  "data": [{"url": "https://cdn.bytespike.ai/img/...", "revised_prompt": "..."}]
}
```

URLs pre-signed, 24h expiry.

## Code examples

<CodeGroup>
  ```bash cURL theme={null}
  curl https://llm.bytespike.ai/v1/images/generations \
    -H "x-api-key: $BYTESPIKE_API_KEY" \
    -H "content-type: application/json" \
    -d '{"model": "nano-banana-v2", "prompt": "A cafe storefront chalk-board menu", "size": "2048x2048"}'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(base_url="https://llm.bytespike.ai/v1", api_key="$BYTESPIKE_API_KEY")
  resp = client.images.generate(
      model="nano-banana-v2",
      prompt="A cafe storefront with a chalk-board menu reading PASTEL DE NATA and AMERICANO",
      size="2048x2048",
  )
  print(resp.data[0].url)
  ```

  ```javascript Node theme={null}
  import OpenAI from "openai"

  const client = new OpenAI({
    baseURL: "https://llm.bytespike.ai/v1",
    apiKey: process.env.BYTESPIKE_API_KEY,
  })
  const resp = await client.images.generate({
    model: "nano-banana-v2",
    prompt: "A cafe storefront with a chalk-board menu reading PASTEL DE NATA and AMERICANO",
    size: "2048x2048",
  })
  console.log(resp.data[0].url)
  ```
</CodeGroup>

## Errors

| Code                  | Trigger                           | Billed?         |
| --------------------- | --------------------------------- | --------------- |
| 400 / 401 / 402 / 403 | Standard                          | No              |
| 451                   | Prompt blocked by upstream safety | No              |
| 5xx                   | Upstream issue                    | No (auto-retry) |

## When to use

* In-image text (signage, packaging, book covers, UI mockups).
* Human subjects where hand / face anatomy must hold up at scale.
* For prior generation hero photography, see [Nano Banana Pro](/api-reference/image/nano-banana-pro).
* For lower cost iteration, see [GPT-Image 2](/api-reference/image/gpt-image-2).

## Limits

| Limit                          | Value                   |
| ------------------------------ | ----------------------- |
| Max output resolution          | 2048×2048               |
| Max images per call (`n`)      | 2                       |
| Supports init image (img2img)  | No                      |
| Supports `quality` modifier    | Yes (`standard` / `hd`) |
| Supports seed reproduction     | Yes                     |
| Sync?                          | Yes (≤45s)              |
| Avg latency for 2048² standard | 14-22s                  |