curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen-image-3.0",
  "prompt": "An orange cat wearing an astronaut helmet, cyberpunk neon background",
  "size": "16:9",
  "quality": "2K"
}
'

{
  "created": 1757156493,
  "id": "task-unified-1757156493-imcg5zqt",
  "model": "qwen-image-3.0",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 30
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_image",
    "credits_reserved": 2.2483,
    "user_group": "default"
  }
}

{
  "error": {
    "code": "invalid_request",
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": "insufficient_quota",
    "message": "Insufficient quota. Please top up your account.",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": "model_access_denied",
    "message": "Token does not have access to model: qwen-image-3.0",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Too many requests, please try again later",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": "internal_error",
    "message": "Internal server error",
    "type": "api_error"
  }
}

Qwen-Image

Qwen Image 3.0

Qwen (qwen-image-3.0) is the standard edition of Qwen image generation and editing 3.0. It supports the same two modes — text-to-image (T2I, no reference image) and image editing (I2I, with 1-3 reference images) — balancing quality and speed
Request parameters, size semantics and response structure are identical to qwen-image-3.0-pro; only generation quality and price differ
Asynchronous processing mode, use the returned task ID to query
Generated image links are valid for 24 hours, please save them promptly

Billing:

Billed as “number of output images × resolution tier”; on the standard edition 1K and 2K cost the same (unlike Pro, where 2K is more expensive)
If reference images are supplied (I2I), each reference image is billed once on top; this charge is independent of n and does not scale with the number of output images
Unit price is lower than Pro — prefer this model when optimizing for cost

POST

images

generations

curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen-image-3.0",
  "prompt": "An orange cat wearing an astronaut helmet, cyberpunk neon background",
  "size": "16:9",
  "quality": "2K"
}
'

{
  "created": 1757156493,
  "id": "task-unified-1757156493-imcg5zqt",
  "model": "qwen-image-3.0",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 30
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_image",
    "credits_reserved": 2.2483,
    "user_group": "default"
  }
}

{
  "error": {
    "code": "invalid_request",
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": "insufficient_quota",
    "message": "Insufficient quota. Please top up your account.",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": "model_access_denied",
    "message": "Token does not have access to model: qwen-image-3.0",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Too many requests, please try again later",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": "internal_error",
    "message": "Internal server error",
    "type": "api_error"
  }
}

Authorizations

Authorization

string

header

required

##All APIs require Bearer Token authentication##

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

default:qwen-image-3.0

required

Model name

Available options:

qwen-image-3.0

Example:

"qwen-image-3.0"

prompt

string

required

Prompt describing the image to generate (text-to-image), or how to edit the input image (image editing). Limited to 4500 tokens

Maximum string length: 4500

Example:

"Replace the background of this image"

image_urls

string<uri>[]

Reference image URL list (optional). Not provided or empty array = text-to-image (T2I); provide 1-3 images = image editing (I2I)

Note:

Number of input images supported per request: 0-3 images, more than 3 will return an error
Only public http/https image URLs are supported, base64 / data-url is not supported
Image width and height must both be within the [384-3072] pixel range
Supported file formats: .jpg, .jpeg, .png, .bmp, .webp, .tiff
Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)

Example:

[
  "https://example.com/image1.png",
  "https://example.com/image2.png"
]

integer

default:1

Specifies the number of images to generate, supports any integer value between [1,6]

Note:

Each request will be pre-charged based on the value of n, actual charges are based on the number of images generated
The reference image (image_urls) charge is billed once per uploaded image and does not scale with n

Required range: 1 <= x <= 6

Example:

1

negative_prompt

string

Negative prompt to describe content you don't want to see in the image, used to constrain the output

Note:

Supports Chinese and English, maximum length of 500 characters, each Chinese character/letter counts as one character, excess will be automatically truncated

Maximum string length: 500

Example:

"low resolution, error, worst quality, low quality, mutilated, extra fingers, bad proportions"

size

string

default:auto

Dimensions of the generated image. Three approaches are supported:

Option 1 - Auto (default):

auto: the model automatically selects an appropriate output size based on the prompt (in this case quality has no effect)

Option 2 - Aspect-ratio format:

1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21
Used together with the quality parameter; the system automatically converts to the pixels corresponding to the chosen ratio and resolution, with no need to specify them manually

Option 3 - Pixel format:

width×height, e.g. 1024x1024, 2048x2048, 2720x1530, etc.
Total pixel range: [262144, 4194304] (i.e. 512×512 to 2048×2048)
Aspect-ratio range: [1/16, 16]; a side may exceed 2048px
Both width and height must be greater than 14px

Note:

size and n are independent; when n>1 you can still specify a size/ratio
When size is omitted, it defaults to auto

Example:

"16:9"

quality

enum<string>

default:1K

Resolution tier, used together with the aspect-ratio format of size; defaults to 1K (has no effect under auto or the pixel format).

Ratio	1K	2K
`1:1`	1024×1024	2048×2048
`2:3`	832×1248	1664×2496
`3:2`	1248×832	2496×1664
`3:4`	864×1152	1770×2360
`4:3`	1152×864	2360×1770
`4:5`	896×1120	1792×2240
`5:4`	1120×896	2240×1792
`9:16`	800×1424	1530×2720
`16:9`	1424×800	2720×1530
`21:9`	1568×672	3122×1338
`9:21`	672×1568	1338×3122

Available options:

1K,

2K

Example:

"2K"

prompt_extend

boolean

default:false

Whether to enable intelligent prompt rewriting. Default value is false (does not rewrite the user's prompt without permission); only when explicitly set to true will a large model be used to optimize the positive prompt, with noticeable improvement for insufficiently descriptive or simpler prompts

Example:

true

watermark

boolean

default:false

Whether to add "Qwen-Image" watermark to the bottom right corner of the image. Default value is false

Example:

false

seed

integer

Random seed, range [0, 2147483647], using the same seed value can keep generated content relatively stable

Note:

If not provided, the algorithm will automatically use a random seed
Model generation process is probabilistic, even with the same seed, results cannot be guaranteed to be completely identical each time

Required range: 0 <= x <= 2147483647

Example:

12345

callback_url

string<uri>

HTTPS callback address after task completion

Callback Timing:

Triggered when task is completed, failed, or cancelled
Sent after billing confirmation is completed

Security Restrictions:

Only HTTPS protocol is supported
Callback to internal IP addresses is prohibited (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
URL length must not exceed 2048 characters

Callback Mechanism:

Timeout: 10 seconds
Maximum 3 retries on failure (retries after 1 second/2 seconds/4 seconds)
Callback response body format is consistent with the task query API response format
Callback address returning 2xx status code is considered successful, other status codes will trigger retry

Example:

"https://your-domain.com/webhooks/image-task-completed"

Response

Image task created successfully

created

integer

Task creation timestamp

Example:

1757156493

string

Task ID

Example:

"task-unified-1757156493-imcg5zqt"

model

string

Actual model name used

Example:

"qwen-image-3.0"

object

enum<string>

Specific task type

Available options:

image.generation.task

progress

integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100

Example:

0

status

enum<string>

Task status

Available options:

pending,

processing,

completed,

failed

Example:

"pending"

task_info

object

Asynchronous task information

Show child attributes

type

enum<string>

Task output type

Available options:

text,

image,

audio,

video

Example:

"image"

usage

object

Usage and billing information

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

Qwen Image 3.0

Authorizations

Body

Response