Imagen 4.0

POST

tasks

Imagen 4.0

curl --request POST \
  --url https://api.qingbo.ai/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "n": 123,
  "seed": 123,
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ]
}
'

import requests

url = "https://api.qingbo.ai/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "n": 123,
    "seed": 123,
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "callback_url": "<string>",
    "callback_events": ["<string>"]
}
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>',
    n: 123,
    seed: 123,
    aspect_ratio: '<string>',
    resolution: '<string>',
    callback_url: '<string>',
    callback_events: ['<string>']
  })
};

fetch('https://api.qingbo.ai/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://api.qingbo.ai/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"seed\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\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://api.qingbo.ai/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"seed\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "imagen-4.0",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

imagen-4.0 was delisted on 2026-09-03; this page is kept for reference only. For Google image generation use the Nano Banana family (Gemini Image Series)

Imagen 4.0 from Google DeepMind — native 2K output, photorealistic lighting and materials, with high accuracy for Chinese and English text rendering. Suited for poster key visuals, marketing hero images, and artistic illustrations where image quality and text rendering matter. Per-image pricing, unified 2K output.

Pricing

Prices are not listed here — they follow upstream changes, and anything written into the docs drifts out of date.Live prices: the “Model Market” in the console, or the GET /v1/models endpoint (see Models). What a call actually cost: every response carries cost / usage.cost — that is the authoritative number.

Examples

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "imagen-4.0",
    "prompt": "Sunrise on a mountaintop, sea of clouds rolling, distant snow peaks glowing gold, photorealistic photography style"
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "imagen-4.0",
    "prompt": "Movie poster, large title \"STARFALL\", subtitle \"Coming 2026\", starry sky background, minimal whitespace",
    "aspect_ratio": "9:16",
    "n": 2
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "imagen-4.0",
    "prompt": "Modern minimalist office, morning light through floor-to-ceiling windows, green plant accents, magazine photography style",
    "aspect_ratio": "16:9",
    "seed": 42
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "imagen-4.0",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

After submission, poll status with GET /v1/tasks/{task_id}. See Task System for details.

Available Models

Model ID	Description
`imagen-4.0`	Google DeepMind flagship text-to-image, native 2K, photorealistic, accurate Chinese and English text

Common Parameters

string

必填

Choose one from the Available Models list

string

默认值:"generate"

generate — text to image (default)
edit — image editing; pair with image_urls

The mode is decided by what you send, not by the action: prompt alone is text-to-image; one image_urls entry is image-to-image; several are multi-image reference; add mask_url for inpainting.

string

必填

Image description. Supports Chinese and English. Imagen 4.0 excels at scene detail, lighting, and text rendering

integer

默认值:"1"

Number of images to generate (returned in a single call)

integer

默认值:"-1"

Random seed. -1 for random; a fixed value reproduces similar results

string

默认值:"1:1"

Aspect ratio. Options:

1:1 — Square
4:3 / 3:4 — Standard landscape / portrait
16:9 / 9:16 — Widescreen landscape / portrait

string

Output resolution. Imagen 4.0 defaults to native 2K with no resolution tiers — leave empty

string

Webhook callback URL, invoked when the task reaches a terminal state. See Callback Mechanism

string[]

Event types to receive callbacks for. Defaults to all terminal events

Resource Limits

Item	Limit
Supported action	`generate` only (text-to-image)
Output resolution	Native 2K (fixed, no tier selection)
Aspect ratio	`1:1` / `4:3` / `3:4` / `16:9` / `9:16` (5 options)
Output file	JPG, URL valid for 24 hours

Task System — Task state machine / polling cadence / async push
Request & Response — Common error codes / Headers / rate limits
Authentication — API Key application and usage

Imagen 4.0

curl --request POST \
  --url https://api.qingbo.ai/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "n": 123,
  "seed": 123,
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ]
}
'

import requests

url = "https://api.qingbo.ai/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "n": 123,
    "seed": 123,
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "callback_url": "<string>",
    "callback_events": ["<string>"]
}
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>',
    n: 123,
    seed: 123,
    aspect_ratio: '<string>',
    resolution: '<string>',
    callback_url: '<string>',
    callback_events: ['<string>']
  })
};

fetch('https://api.qingbo.ai/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://api.qingbo.ai/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"seed\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\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://api.qingbo.ai/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"seed\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "imagen-4.0",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

开始

核心概念

Pricing

Examples

Available Models

Common Parameters

Resource Limits

​Pricing

​Examples

​Available Models

​Common Parameters

​Resource Limits

​Related Docs

Pricing

Examples

Available Models

Common Parameters

Resource Limits

Related Docs