Skip to main content
POST
/
v1
/
images
/
generations
curl --request POST \
  --url https://api.apimart.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen-image-2.0",
    "prompt": "A cute orange cat napping in the sunshine"
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01JGXYZ1234567890ABCDEF"
    }
  ]
}

curl --request POST \
  --url https://api.apimart.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen-image-2.0",
    "prompt": "A cute orange cat napping in the sunshine"
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01JGXYZ1234567890ABCDEF"
    }
  ]
}

​
Supported Models

ModelDescriptionMax ImagesPricing
qwen-image-2.0Standard version, balanced quality and performance6Fixed price
qwen-image-2.0-proPro version, stronger text rendering, more refined realistic textures6Fixed price

​
Authorizations

​
Authorization
string
required
All endpoints require Bearer Token authenticationGet API Key:Visit API Key Management to get your API KeyAdd to request header:
Authorization: Bearer YOUR_API_KEY

​
Body

​
model
string
required
Model name
  • qwen-image-2.0 - Standard version, balanced quality and performance
  • qwen-image-2.0-pro - Pro version, stronger text rendering, more refined realistic textures
​
prompt
string
required
Text description for image generation, up to 800 characters
​
size
string
default:"1:1"
Image aspect ratioSupported aspect ratios:
  • 1:1 - Square (default)
  • 4:3 - Landscape 4:3
  • 3:4 - Portrait 3:4
  • 16:9 - Landscape widescreen
  • 9:16 - Portrait vertical
  • 3:2 - Landscape 3:2
  • 2:3 - Portrait 2:3
​
resolution
string
default:"1K"
Resolution tier
  • 1K - Standard resolution (default)
  • 2K - High definition resolution
​
n
integer
default:"1"
Number of images to generateRange: 1-6
​
negative_prompt
string
Negative prompt (content you don’t want to appear), up to 500 characters
​
image_urls
array
Reference image URL array (image-to-image mode)Limitations:
  • Must be publicly accessible URLs
  • Base64 format not supported

​
Resolution Reference Table

Output size is controlled by the combination of size (ratio) + resolution (resolution tier).
Ratio1K Tier2K Tier
1:11024×10242048×2048
4:31152×8642048×1536
3:4864×11521536×2048
16:91280×7202048×1152
9:16720×12801152×2048
3:21248×8322048×1360
2:3832×12481360×2048
  • Only size → defaults to 1K tier: {"size": "16:9"} → 1280×720
  • size + resolution → specified tier: {"size": "16:9", "resolution": "2K"} → 2048×1152

​
Usage Examples

Text-to-Image (minimal request) 
{
  "model": "qwen-image-2.0",
  "prompt": "A cute orange cat napping in the sunshine"
}
Specify ratio and count 
{
  "model": "qwen-image-2.0-pro",
  "prompt": "Cyberpunk-style futuristic city nightscape with flickering neon lights",
  "size": "16:9",
  "n": 4
}
High definition 2K tier 
{
  "model": "qwen-image-2.0-pro",
  "prompt": "Exquisite food photography, sushi platter",
  "size": "4:3",
  "resolution": "2K",
  "n": 2
}
Image-to-Image (reference image + text description) 
{
  "model": "qwen-image-2.0",
  "prompt": "Change the background to a seaside sunset",
  "image_urls": ["https://example.com/my-photo.jpg"]
}

​
Response

​
code
integer
Response status code
​
data
array
Response data array

​
Notes

  1. Asynchronous Processing: After submission, a task_id is returned. Poll /v1/tasks/{task_id} to get results
  2. Image Storage: Generated images are mirrored to platform CDN and are valid long-term
  3. Billing Rules: Billed per successfully generated image, no charge for failures
  4. Image URL Requirements: Input images must be publicly accessible URLs, base64 not supported