Qwen Image Series

POST

tasks

Qwen Image Series

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

import requests

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

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "n": 123,
    "negative_prompt": "<string>",
    "prompt_extend": True,
    "prompt_extend_mode": "<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>',
    image_urls: ['<string>'],
    aspect_ratio: '<string>',
    resolution: '<string>',
    n: 123,
    negative_prompt: '<string>',
    prompt_extend: true,
    prompt_extend_mode: '<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  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"negative_prompt\": \"<string>\",\n  \"prompt_extend\": true,\n  \"prompt_extend_mode\": \"<string>\"\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  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"negative_prompt\": \"<string>\",\n  \"prompt_extend\": true,\n  \"prompt_extend_mode\": \"<string>\"\n}")
  .asString();

Qwen Image is the image foundation model line from Alibaba’s Qwen team. It unifies text-to-image generation and image editing behind one interface and is strongest at bilingual (Chinese and English) typography, infographics and text inside posters. This page covers the four models available today, in two generations, both returning one to six images per request: the 2.0 generation settles at a single per-image price, while the 3.0 generation adds multi-reference editing and prompt expansion and prices reference images separately.

Quick start

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: qwen-image-demo-001" \
  -d '{
    "model": "qwen-image-3.0",
    "action": "generate",
    "prompt": "A cafe menu poster, bilingual, serif headings, two-column body text",
    "aspect_ratio": "3:4",
    "resolution": "2k",
    "n": 1
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: qwen-image-edit-001" \
  -d '{
    "model": "qwen-image-3.0-pro",
    "action": "edit",
    "prompt": "Place the product from the first image on the display stand in the second, matching the lighting",
    "image_urls": [
      "https://cdn.example.com/product.png",
      "https://cdn.example.com/scene.png"
    ],
    "aspect_ratio": "1:1",
    "resolution": "1k"
  }'

curl -X POST https://api.qingbo.ai/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-2.0",
    "action": "generate",
    "prompt": "A flat-illustration city skyline in four colour variants",
    "negative_prompt": "text, watermark",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "n": 4
  }'

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 qwen-image-2.0, qwen-image-2.0-pro, qwen-image-3.0 or qwen-image-3.0-pro.

string

default:"generate"

generate: create an image from text
edit: rewrite reference images; requires image_urls

string

required

The image description or editing instruction, in Chinese or English.

string[]

Reference image URLs. qwen-image-2.0 and qwen-image-2.0-pro require at least one on edit. qwen-image-3.0 and qwen-image-3.0-pro require one to three of them on edit and accept none on generate.

string

Framing: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3. qwen-image-3.0 and qwen-image-3.0-pro default to 1:1.

string

Output resolution, 1k or 2k. qwen-image-3.0 and qwen-image-3.0-pro default to 1k.

integer

default:"1"

Number of images to generate; all four models accept 1–6.

string

Content to avoid in the generated result, up to 500 characters.

boolean

default:"false"

Let the model expand the prompt; disabled by default. Supported by qwen-image-3.0 and qwen-image-3.0-pro only.

string

Prompt expansion mode, direct or agent. Supported by qwen-image-3.0 and qwen-image-3.0-pro only, requires prompt_extend: true, and edit accepts direct only.

See Submit a task for callback_url, callback_events, Prefer: wait, Idempotency-Key and the maximum-cost header. This series does not accept seed, quality, watermark or mask_url. Any other parameter returns 400 and is not billed.

Limits

Condition	Limit
`qwen-image-2.0` / `qwen-image-2.0-pro`	Up to 6 images per request
`action: "edit"` (both 2.0 models)	Image editing requires at least one reference image
`qwen-image-3.0` / `qwen-image-3.0-pro`	A prompt is required; 1 to 6 images per request.
`action: "generate"` (both 3.0 models)	Text-to-image does not take reference images; use `edit`
`action: "edit"` (both 3.0 models)	Image editing requires 1 to 3 reference images
`prompt_extend_mode`	Requires `prompt_extend=true`
`prompt_extend_mode` on `edit`	Image editing accepts `direct` prompt extension only

Pricing

Billed at a fixed price per successfully generated image. Rates are in price_config on GET /v1/models and in the console’s Model Market. 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. The billing dimensions differ by generation:

qwen-image-2.0 / qwen-image-2.0-pro — one per-image price; 1k and 2k cost the same, and neither aspect ratio nor prompt length affects it. The total is that price times n.
qwen-image-3.0 — 1k and 2k cost the same; the output part is the per-image price × n.
qwen-image-3.0-pro — 2k costs more than 1k; the output part is the per-image price × n.
Reference images on both 3.0 models — each reference image in the request adds its own per-image fee on top of the output images, charged once per request and not repeated for each of the n outputs. generate carries no reference images and no such fee.

A resolution outside the tiers a model supports settles at its fallback price, equal to that model’s base tier. 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": "task-wave1789004688b950049238",
  "model": "qwen-image-3.0",
  "action": "edit",
  "status": "completed",
  "progress": "100%",
  "created_at": 1788754231,
  "completed_at": 1788754266,
  "result": {
    "images": [
      {
        "expires_at": 1789089508,
        "url": ["https://cdn.example.com/result.png"]
      }
    ]
  },
  "urls": {
    "get": "https://api.qingbo.ai/v1/tasks/task-wave1789004688b950049238",
    "cancel": "https://api.qingbo.ai/v1/tasks/task-wave1789004688b950049238/cancel"
  },
  "billing_status": "settled",
  "cost": 12377
}

Generated images come back in result.images, and expires_at is when that link stops working. With n greater than 1 the images array holds several entries. See Query Task Status for the full field list.

Available models

Model ID	Resolutions	`n`	Reference images	Line-specific parameters
`qwen-image-2.0`	`1k` `2k` (same price)	1–6	Supplied on `edit`	`negative_prompt`
`qwen-image-2.0-pro`	`1k` `2k` (same price)	1–6	Supplied on `edit`	`negative_prompt`
`qwen-image-3.0`	`1k` `2k` (same price)	1–6	1–3, billed separately	`negative_prompt` `prompt_extend` `prompt_extend_mode`
`qwen-image-3.0-pro`	`1k` `2k` (`2k` costs more)	1–6	1–3, billed separately	`negative_prompt` `prompt_extend` `prompt_extend_mode`

All four support generate and edit and share the same aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3.

Qwen Image Series

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

import requests

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

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "image_urls": ["<string>"],
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "n": 123,
    "negative_prompt": "<string>",
    "prompt_extend": True,
    "prompt_extend_mode": "<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>',
    image_urls: ['<string>'],
    aspect_ratio: '<string>',
    resolution: '<string>',
    n: 123,
    negative_prompt: '<string>',
    prompt_extend: true,
    prompt_extend_mode: '<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  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"negative_prompt\": \"<string>\",\n  \"prompt_extend\": true,\n  \"prompt_extend_mode\": \"<string>\"\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  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"n\": 123,\n  \"negative_prompt\": \"<string>\",\n  \"prompt_extend\": true,\n  \"prompt_extend_mode\": \"<string>\"\n}")
  .asString();

Text Generation

Image Generation

Video Generation

Audio

Tools & Embeddings

Task Management

Account & Usage

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