Qwen Image 2.0 API
Qwen Image 2.0 (qwen-image-2.0) is Alibaba's Qwen image model for text to image and image editing in one model. Use the Qwen Image API to render readable text in posters, infographics and slides, or edit a photo with a plain-language instruction, at 1K or 2K.
Service Highlights
- Official Discounts
- Pay-as-you-go
- Fast & Low Latency
Image link valid for 72 hours
Qwen Image 2.0 API Pricing
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
qwen-image-2.0 | 1K/2K | 0.2Credits(~$0.02)/pic | 0.19Credits(~$0.019)/pic | 0.18Credits(~$0.018)/pic | 0.25Credits(~$0.025)/pic | 20% |
* Actual costs are subject to final output.
Qwen Image 2.0 API - Text-Rich Images and Natural-Language Editing
Qwen Image 2.0 API by Alibaba: create posters, infographics and slides with readable in-image text, then edit images by describing the change in plain language. One endpoint handles text to image and image to image, with 1–6 images per request at 1K or 2K. Save 20% or more with membership.
50K+
Active Users
99.9%
Uptime
2x
Faster
20%
Cost Savings
Qwen Image 2.0 API Example: Text to Image and Image Editing
Call qwen-image-2.0 on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint for the Qwen Image 2.0 image URL.
- 1
Authenticate Qwen Image API requests
Save the key you created above in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
- 2
Submit a Qwen Image 2.0 task
POST /v1/images/generations with model qwen-image-2.0, your prompt, size and resolution. Add image_urls to edit an existing image. The response returns a task_id.
- 3
Get the Qwen Image 2.0 result
Send GET /v1/tasks/{task_id} until status is completed, then read the image URL from data.result.images[0].url[0]. Generated images are mirrored to the APIMart CDN. Failed tasks are not charged.
See the Qwen Image 2.0 API reference for every parameter and response field.
curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-image-2.0",
"prompt": "A minimalist coffee shop poster with the headline OPEN LATE and the line Fresh espresso until 2 AM, warm brown tones, clean sans-serif type",
"n": 1,
"size": "3:4",
"resolution": "2K"
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "qwen-image-2.0",
"prompt": "A minimalist coffee shop poster with the headline OPEN LATE and the line Fresh espresso until 2 AM, warm brown tones, clean sans-serif type",
"n": 1,
"size": "3:4",
"resolution": "2K"
}
resp = requests.post(f"{API_BASE}/v1/images/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["images"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(3)
else:
raise TimeoutError(f"task {task_id} did not finish in time")curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-image-2.0",
"prompt": "Change the background to a beach at sunset and keep the person unchanged",
"n": 1,
"image_urls": [
"https://example.com/my-photo.jpg"
]
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"Qwen Image 2.0 API Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: qwen-image-2.0 | Model ID. Use qwen-image-2.0; qwen-image-2.0-pro takes the same parameters. |
prompt | string | Required | Default: — | Text description of the image, or the edit instruction when image_urls is set. Up to 800 characters. |
size | string | Optional | Default: 1:1 | Aspect ratio: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2 or 2:3. |
resolution | string | Optional | Default: 1K | Resolution tier: 1K or 2K. For example, 16:9 is 1280×720 in 1K and 2048×1152 in 2K. |
n | integer | Optional | Default: 1 | Number of images to generate, 1–6. |
negative_prompt | string | Optional | Default: — | Content you do not want in the image. Up to 500 characters. |
image_urls | array | Optional | Default: — | Reference images for image to image editing, up to 3. Must be publicly accessible URLs; base64 is not supported. |
nsfw_check | boolean | Optional | Default: false | Set to true to moderate the prompt and input images before the task is submitted. |
