Qwen Image 2 API
by Alibaba
Alibaba's next-generation image foundation model (Feb 2026), officially Qwen-Image-2.0, a lightweight unified generation-and-editing model known for professional text rendering and native 2K output.
- ~14s
- Avg. generation
- 4 credits
- From
Image · example Playground
Try Qwen Image 2 right here.
Your output lands here. Hit generate to run this request in Studio.
Pricing
Simple per-generation pricing.
4 credits per generation ≈ $0.04
- You only pay for successful generations. Failed jobs are refunded automatically.
- One credit balance across every model on Apiframe, no per-model plans.
- Start with free credits. No subscription required.
- Volume discounts on larger plans.
Specs
At a glance.
Quickstart
How to call the Qwen Image 2 API.
Send one POST /v2/images/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.
Swap qwen-image-2 for any other model and nothing else changes.
const response = await fetch("https://api.apiframe.ai/v2/images/generate", {
method: "POST",
headers: {
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
"model": "qwen-image-2",
"qwenParams": {
"image": "https://example.com/input.jpg",
"negative_prompt": "What you do NOT want to see…",
"seed": 1
}
}),
});
const { jobId } = await response.json();
console.log(jobId); Input schema
Every field Qwen Image 2 accepts, with types and defaults. The full reference lives in the docs.
| Field | Type | Description |
|---|---|---|
| prompt required | string | Text description of what to generate. |
| model required | string | The model identifier for this endpoint. Default:"qwen-image-2" · "qwen-image-2" |
| qwenParams.image | string (URL) | Reference image (URL) |
| qwenParams.negative_prompt | string | Negative prompt |
| qwenParams.seed | number | Reuse a number to reproduce the same result. step 1 |
Qwen versions
Every Qwen image model on Apiframe. Switch with one parameter.
Qwen Image 2 questions
What teams ask before shipping with Qwen Image 2. Everything else lives in the docs.
What is Qwen Image 2?
Alibaba's Qwen-Image-2.0, released in February 2026, a unified image generation and editing foundation model.
How is it different from the original Qwen-Image?
It unifies generation and editing, runs on a lighter 7B architecture instead of 20B, and significantly improves text rendering and resolution.
What is it best at?
Professional typography and text layout, including infographics, slides, posters, comics, and bilingual designs.
What resolution does it produce?
Native 2K, at 2048x2048.
Can it edit images, not just generate them?
Yes. Generation and editing are combined in a single model.
Where can you access it?
Through Apiframe, as well as the Alibaba Cloud BaiLian API and Qwen Chat.
Related models
All image modelsFlux 2 Max
by Black Forest Labs
Highest-quality Flux 2 tier.
View modelMidjourney
by Midjourney
Iconic stylised, cinematic look.
View modelNano Banana 2
by Google
Next-gen Nano Banana with refined detail.
View modelSeedream 5.0 Pro
by ByteDance
Flagship ByteDance model with sharp 1K/2K output and up to 10 reference images.
View model9,800+
developers & companies
Official partner of
Power your next AI product with Apiframe.
Instant access to 70+ media models through a single API. Start free and scale when you're ready.