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

# Nano Banana Economy

> Nano Banana (Gemini Image) economy routes: fixed per-image pricing for text-to-image and multi-reference editing

Nano Banana is Google's Gemini image model line. This page covers the **four economy models**. They share one set of request parameters and one billing model (a fixed price per successful image) and differ only in aspect ratios, resolutions and line-specific parameters — switching tiers means changing `model` and nothing else. To be billed from actual token usage instead, use [Nano Banana Official](/en/api-reference/image/gemini/nano-banana).

<Note>
  The economy line is not Google's official API, and the two lines never switch automatically: the model ID selects the line.
</Note>

## Quick start

<CodeGroup>
  ```bash Text to image theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -H "Idempotency-Key: nb-demo-001" \
    -d '{
      "model": "gemini-3.1-flash-image-rev",
      "action": "generate",
      "prompt": "A celadon teacup on an oak table, natural window light, product photography",
      "aspect_ratio": "1:1",
      "resolution": "1k",
      "n": 1
    }'
  ```

  ```bash Edit with a reference theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -H "Idempotency-Key: nb-edit-001" \
    -d '{
      "model": "gemini-3.1-flash-image-rev",
      "action": "edit",
      "prompt": "Keep the subject, replace the background with a bamboo grove at dawn",
      "image_urls": ["https://cdn.example.com/source.png"],
      "aspect_ratio": "1:1",
      "resolution": "1k",
      "n": 1
    }'
  ```

  ```bash Multiple references theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gemini-3-pro-image-rev",
      "action": "edit",
      "prompt": "Place the person from the first image into the scene from the second, matching the light",
      "image_urls": [
        "https://cdn.example.com/person.png",
        "https://cdn.example.com/scene.png"
      ],
      "aspect_ratio": "16:9",
      "resolution": "2k"
    }'
  ```

  ```bash Grounded in web search theme={"system"}
  curl -X POST https://www.qingbo.dev/v1/tasks \
    -H "Authorization: Bearer $WAVE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gemini-3.1-flash-image-rev",
      "action": "generate",
      "prompt": "An infographic of the ten scenic spots of West Lake, with accurate labels",
      "aspect_ratio": "4:5",
      "resolution": "2k",
      "google_search": true,
      "google_image_search": true
    }'
  ```
</CodeGroup>

A successful submission returns a `task_id`. Retrieve the result with [`GET /v1/tasks/{task_id}`](/en/api-reference/task/status), wait inline with [`Prefer: wait`](/en/api-reference/task/submit#in-request-waiting-prefer-wait), or configure a webhook.

## Request parameters

<ParamField body="model" type="string" required>
  One of `gemini-3-pro-image-rev`, `gemini-3.1-flash-image-rev`, `gemini-3.1-flash-lite-image-rev` or `gemini-2.5-flash-image-preview-rev`.
</ParamField>

<ParamField body="action" type="string" default="generate">
  * `generate` — generate from text
  * `edit` — rewrite from reference images; `image_urls` is required

  Image-to-image and multi-reference blending both use `edit`; the only difference is how many entries `image_urls` carries.
</ParamField>

<ParamField body="prompt" type="string" required>
  Image description or editing instruction, in English or Chinese.
</ParamField>

<ParamField body="image_urls" type="string[]">
  Reference image URLs. Required for `edit`, up to 14 on all four tiers. Reference images carry no extra charge.
</ParamField>

<ParamField body="aspect_ratio" type="string" default="1:1">
  Frame ratio. Eleven are shared by all four tiers: `auto`, `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9`.

  `gemini-3.1-flash-image-rev` additionally supports `1:4`, `4:1`, `1:8` and `8:1`.

  `auto` lets the model decide: it picks from the prompt for text-to-image, and follows the input image for edits. On `gemini-2.5-flash-image-preview-rev`, omitting the parameter also leaves the ratio to the model.
</ParamField>

<ParamField body="resolution" type="string" default="1k">
  Output resolution; the default is `1k` on all three tiers that accept it. The tiers each model offers are listed under "Available models": `1k`, `2k` and `4k` on the flagship tier, `0.5k`, `1k`, `2k` and `4k` on the fast tier, and `1k` only on the previous-generation tier.

  `gemini-3.1-flash-lite-image-rev` does not support this parameter and always outputs 1K; sending it returns `400`.
</ParamField>

<ParamField body="n" type="integer" default="1">
  Number of images to generate. Value: `1`. Each request returns one image.
</ParamField>

<ParamField body="google_search" type="boolean" default="false">
  Search the web for text context before generating. Only `gemini-3.1-flash-image-rev` accepts this parameter.
</ParamField>

<ParamField body="google_image_search" type="boolean" default="false">
  Search the web for reference images; requires `google_search: true`. Only `gemini-3.1-flash-image-rev` accepts this parameter.
</ParamField>

See [Submit a task](/en/api-reference/task/submit) for `callback_url`, `callback_events`, `Prefer: wait`, `Idempotency-Key` and the maximum-cost header.

<Warning>
  The economy line does not support `mask_url`, `quality` or `seed`. `google_search` and `google_image_search` are accepted only by `gemini-3.1-flash-image-rev`; the other three tiers return `400` for them. Any other parameter returns `400` and is not billed. For masked inpainting use [`gpt-image-2`](/en/api-reference/image/gpt-image/gpt-image-2).
</Warning>

## Limits

| Condition        | Limit                                                                                                       |
| ---------------- | ----------------------------------------------------------------------------------------------------------- |
| Per request      | One image per request.                                                                                      |
| `action: "edit"` | Add at least one reference image to edit                                                                    |
| Reference images | Up to 14                                                                                                    |
| Resolution       | Tiers per model are listed under "Available models"; `gemini-3.1-flash-lite-image-rev` rejects `resolution` |

## Pricing

Billed at a **fixed price per successfully generated image**. `generate` and `edit` cost the same, reference images add no fee, and aspect ratio, prompt length and web search have no effect on the price — **resolution is the only billing dimension, so the cost of a call is known before it is submitted**.

The tiers price differently:

| Model ID                             | Price tiers                                                          |
| ------------------------------------ | -------------------------------------------------------------------- |
| `gemini-3-pro-image-rev`             | `1k` and `2k` cost the same; `4k` is its own tier                    |
| `gemini-3.1-flash-image-rev`         | `0.5k` and `1k` cost the same; `2k` and `4k` are each their own tier |
| `gemini-3.1-flash-lite-image-rev`    | A single 1K tier                                                     |
| `gemini-2.5-flash-image-preview-rev` | One price                                                            |

Rates are in `price_config` on `GET /v1/models` and in the console's Model Market. A resolution that `price_config.image_prices` does not list separately settles at the `default` price alongside it. What a single call actually cost is the `cost` field on the task response — an integer quota at **500,000 quota = 1 USD**, not dollars.

You are only billed for a successfully generated image. Failed and cancelled tasks, and tasks that return no usable image, are refunded in full.

## Response

```json Completed task theme={"system"}
{
  "task_id": "taski_example",
  "model": "gemini-3-pro-image-rev",
  "action": "edit",
  "status": "completed",
  "progress": "100%",
  "created_at": 1788686741,
  "completed_at": 1788686763,
  "billing_status": "settled",
  "cost": 16875,
  "result": {
    "images": [
      {
        "expires_at": 1788992341,
        "url": ["https://cdn.example.com/result.png"]
      }
    ]
  },
  "urls": {
    "get": "https://www.qingbo.dev/v1/tasks/taski_example",
    "cancel": "https://www.qingbo.dev/v1/tasks/taski_example/cancel"
  }
}
```

Generated images come back in `result.images`, where `url` is an array and `expires_at` is when the link stops working. See [Query Task Status](/en/api-reference/task/status) for the full field list.

## Available models

| Model ID                             | Tier                | Aspect ratios | Resolutions           | Line-specific parameters              |
| ------------------------------------ | ------------------- | ------------- | --------------------- | ------------------------------------- |
| `gemini-3-pro-image-rev`             | Flagship            | 11            | `1k` `2k` `4k`        | —                                     |
| `gemini-3.1-flash-image-rev`         | Fast                | **15**        | `0.5k` `1k` `2k` `4k` | `google_search` `google_image_search` |
| `gemini-3.1-flash-lite-image-rev`    | Lightest            | 11            | 1K only               | —                                     |
| `gemini-2.5-flash-image-preview-rev` | Previous generation | 11            | `1k`                  | —                                     |

All four do text-to-image and reference-image editing, one image per request.

* **The 11 shared aspect ratios**: `auto` `1:1` `2:3` `3:2` `3:4` `4:3` `4:5` `5:4` `9:16` `16:9` `21:9`
* **The fast tier adds four extreme ratios**: `1:4` `4:1` `1:8` `8:1`, for long horizontal and vertical banners
* **The lightest tier does not accept `resolution`** and always outputs 1K
* **Up to 14 reference images**, the same on all four tiers

## Related

* [Gemini Image Series](/en/api-reference/image/gemini/overview)
* [Nano Banana Official](/en/api-reference/image/gemini/nano-banana)
* [Submit Task](/en/api-reference/task/submit)
* [Query Task Status](/en/api-reference/task/status)
* [Task System](/en/docs/task-system)