MiniMax H3 Image Generation

curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "minimax-h3-image",
  "prompt": "A beautiful colorful sunset over the ocean"
}
'

{
  "created": 1757156493,
  "id": "task-unified-1757156493-imcg5zqt",
  "model": "minimax-h3-image",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 100
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 2.5,
    "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: minimax-h3-image",
    "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"
  }
}

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": "minimax-h3-image",
  "prompt": "A beautiful colorful sunset over the ocean"
}
'

{
  "created": 1757156493,
  "id": "task-unified-1757156493-imcg5zqt",
  "model": "minimax-h3-image",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 100
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 2.5,
    "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: minimax-h3-image",
    "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:minimax-h3-image

required

Image generation model name. The official channel offers better stability and control for commercial use

Available options:

minimax-h3-image

Example:

"minimax-h3-image"

prompt

string

required

Prompt describing the image to generate or how to edit the input images

Length limits:

Up to 32,000 characters (counted as Unicode code points)
When prompt_extend is false, only approximately the first 4096 tokens of the prompt take effect

Maximum string length: 32000

Example:

"A beautiful colorful sunset over the ocean"

image_urls

string<uri>[]

List of reference image URLs for image-to-image generation and image editing

Notes:

Number of input images per request: 1~16
Maximum size per image: 64MB
Width and height of each image: 128 to 8192 px
Aspect ratio of each image: longest side / shortest side must not exceed 4:1
Supported formats: .jpeg, .jpg, .png, .webp, .heic, .heif
Image URLs must be directly accessible by the server or trigger a direct download (these URLs usually end in an image extension such as .png or .jpg)
Reference images incur additional image input tokens in image-to-image generation and image editing

Example:

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

size

string

default:auto

Output image size. Supports aspect ratios and explicit pixel dimensions. Default: auto

① Aspect ratio (recommended): X:Y. Common ratios:

1:1: square
1:2 / 2:1: tall / wide
1:3 / 3:1: extra tall / extra wide (at the 3:1 limit)
2:3 / 3:2: standard portrait / landscape
3:4 / 4:3: traditional portrait / landscape
4:5 / 5:4: common social media formats
9:16 / 16:9: mobile / desktop widescreen
9:21 / 21:9: ultrawide formats

Other X:Y values are also supported: X and Y must be integers from 1 to 300, with an aspect ratio ≤ 3:1

② Explicit pixel dimensions: WxH (or W×H), such as 1024x1024, 2720x1536, 5472x3072

Pixel budget: 655,360 ≤ width × height ≤ 20,000,000 (approximately 0.65 MP to 20 MP)
Aspect ratio: ≤ 3:1

③ auto: the model chooses the aspect ratio automatically; the output area still follows the resolution tier

Out-of-range sizes:

Sizes outside these limits return 400; they are not automatically resized or rounded

Example:

"auto"

resolution

enum<string>

default:2K

Resolution shortcut. Applies when size is auto or an aspect ratio; ignored when explicit pixel dimensions are used

Pixel budget (width and height are calculated from the target total pixel count and the size ratio):

1K: ~1 MP (1024² = 1,048,576 pixels)
2K: ~4 MP (2048² = 4,194,304 pixels)
4K: ~16.8 MP (4096² = 16,777,216 pixels)

Actual landscape / square output sizes (portrait sizes swap the corresponding width and height; for example, 3:4 reverses 4:3):

Aspect ratio	2K	4K
`1:1`	2048×2048	4096×4096
`4:3`	2368×1760	4736×3552
`16:9`	2720×1536	5472×3072
`3:1`	3552×1184	7104×2368

Notes:

1K and 2K use the same number of image output tokens (approximately 4,096 per image); 4K uses approximately 16,384 per image. The returned usage is authoritative
Values are case-insensitive

Available options:

1K,

2K,

4K

Example:

"2K"

output_format

enum<string>

default:jpeg

Output image format. Default: jpeg

jpeg: lossy compression, smaller files
png: lossless
webp: balance of file size and quality

Note:

Transparent backgrounds are not supported

Available options:

jpeg,

png,

webp

Example:

"jpeg"

integer

default:1

Number of images to generate. Each image is billed separately

Notes:

Both text input tokens and image input tokens scale proportionally with n
If some images fail (for example, due to content safety checks), the task still completes with the successful images. The actual count is determined by results in the response, and billing follows the returned usage

Required range: 1 <= x <= 10

Example:

1

prompt_extend

boolean

default:true

Prompt enhancement: the model rewrites the prompt with more detail before generation. Default: true

Notes:

Can only be set to false for text-to-image generation when size is an aspect ratio or explicit pixel dimensions
Setting it to false when size is auto or image_urls is provided returns 400
When enabled, it adds approximately 2,300 to 3,800 text input tokens per image; when disabled, only the original prompt is counted

Example:

true

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 generation 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:

"minimax-h3-image"

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

MiniMax H3 Image Generation

Authorizations

Body

Response