Nano Banana Economy

POST

tasks

Nano Banana Economy

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "image_urls": [
    "<string>"
  ],
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "n": 123,
  "google_search": true,
  "google_image_search": true
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "n": 123,
    "google_search": True,
    "google_image_search": True
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    image_urls: ['<string>'],
    aspect_ratio: '<string>',
    resolution: '<string>',
    n: 123,
    google_search: true,
    google_image_search: true
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"google_search\": true,\n  \"google_image_search\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"google_search\": true,\n  \"google_image_search\": true\n}")
  .asString();

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.

The economy line is not Google’s official API, and the two lines never switch automatically: the model ID selects the line.

Quick start

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
  }'

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
  }'

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"
  }'

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
  }'

A successful submission returns a task_id. Retrieve the result with GET /v1/tasks/{task_id}, wait inline with Prefer: wait, or configure a webhook.

Request parameters

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.

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.

string

required

Image description or editing instruction, in English or Chinese.

string[]

Reference image URLs. Required for edit, up to 14 on all four tiers. Reference images carry no extra charge.

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.

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.

integer

default:"1"

Number of images to generate. Value: 1. Each request returns one image.

boolean

default:"false"

Search the web for text context before generating. Only gemini-3.1-flash-image-rev accepts this parameter.

boolean

default:"false"

Search the web for reference images; requires google_search: true. Only gemini-3.1-flash-image-rev accepts this parameter.

See Submit a task for callback_url, callback_events, Prefer: wait, Idempotency-Key and the maximum-cost header.

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.

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

Completed task

{
  "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 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

Nano Banana Economy

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "image_urls": [
    "<string>"
  ],
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "n": 123,
  "google_search": true,
  "google_image_search": true
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "n": 123,
    "google_search": True,
    "google_image_search": True
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    image_urls: ['<string>'],
    aspect_ratio: '<string>',
    resolution: '<string>',
    n: 123,
    google_search: true,
    google_image_search: true
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"google_search\": true,\n  \"google_image_search\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"google_search\": true,\n  \"google_image_search\": true\n}")
  .asString();

Text Generation

Image Generation

Video Generation

Audio

Tools & Embeddings

Task Management

Account & Usage

Nano Banana Economy

Quick start

Request parameters

Limits

Pricing

Response

Available models

​Quick start

​Request parameters

​Limits

​Pricing

​Response

​Available models

​Related

Quick start

Request parameters

Limits

Pricing

Response

Available models

Related