curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "mj-v8.2",
  "prompt": "A cinematic shot of a Maine Coon cat on a neon-lit balcony --ar 16:9 --s 500",
  "quality": "standard",
  "model_params": {
    "speed": "fast"
  }
}
'

{
  "created": 1757165031,
  "id": "task-unified-1757165031-mjv82",
  "model": "mj-v8.2",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "estimated_time": 45
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 1.8,
    "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: mj-v8.2",
    "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"
  }
}

Midjourney V8.2

Midjourney V8.2 Image Generation

Midjourney V8.2 model supports generating high-quality images via natural language prompts. Fast mode returns 4 images per generation; Draft mode returns 24 lightweight 512 px sketch images in a single run
Supports text-to-image and image-to-image (reference image URLs in prompt)
Input image URLs must be publicly reachable and fetchable within about 10 seconds; the upstream fetches images synchronously at task creation and returns 400 if it cannot. Image hosts outside mainland China (imgur, ibb, raw.githubusercontent, pinimg, picsum) fail in practice. Host images on a fast CDN or use the platform file upload
V8.2 highlights: an aesthetics and image-quality upgrade over V8.1, a detail level set with the native --quality / --q parameter (1–4, 4 = high-quality mode) in the prompt at no extra cost, and native 2K output (quality=hd). Turbo is not available on V8.2 (the upstream documents V8 as not supporting turbo)
Style Reference (--sref) is supported; --oref / --cref are not supported on V8.2 and are rejected by the upstream, see Prompt Parameter Guide
Prompt parameters that the upstream does not support are passed through as-is: the task fails with a parameter error (invalid_parameters) and reserved credits are refunded (they are no longer silently dropped)
Async processing mode, use the returned task ID to query status
Generated image links are valid for 30 days, please save them promptly
Timeout: approximately 20 minutes
Parameter notes: this route runs on V8.2 and does not support niji; set the speed mode via model_params.speed and the output quality via the top-level quality parameter; the detail level is written in the prompt as --quality / --q (1–4) and passed through unchanged
mj-v8.2-edit / mj-v8.2-upload-paint are canvas edits (img_pos + mask). The upstream’s instruction-based edit endpoint (--edit, up to 4 reference images) is not exposed on this route yet and is being scheduled

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": "mj-v8.2",
  "prompt": "A cinematic shot of a Maine Coon cat on a neon-lit balcony --ar 16:9 --s 500",
  "quality": "standard",
  "model_params": {
    "speed": "fast"
  }
}
'

{
  "created": 1757165031,
  "id": "task-unified-1757165031-mjv82",
  "model": "mj-v8.2",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "estimated_time": 45
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 1.8,
    "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: mj-v8.2",
    "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"
  }
}

Midjourney has a built-in content moderation system. Each image is moderated individually: filtered images are left out of the results and the remaining images are delivered normally, so you may receive fewer images than usual. If at least one image passes, the task is completed and billed normally; if all images are filtered, the task ends as failed and the reserved credits are refunded in full. Please make sure your prompts and reference images comply with the content guidelines.

Authorizations

Authorization

string

header

required

All endpoints 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:mj-v8.2

required

Model name

Available options:

mj-v8.2

prompt

string

required

Prompt, supports all Midjourney V8.2 native parameter syntax (e.g. --ar 16:9 --s 500).

Image-to-Image: Place image URLs at the beginning of the prompt. Supported formats: .png, .gif, .webp, .jpg, .jpeg

Image-to-Image Rules:

1 image + no text = invalid (will return error)
1 image + text description = valid
2+ images + no text = valid
2+ images + text description = valid

Unsupported parameters: parameters the upstream does not support (e.g. --oref, --cref, --stop, --bs) are passed through and explicitly rejected by the upstream: the task fails with a parameter error (invalid_parameters) and reserved credits are refunded. --v / --version / --niji and the speed / hd parameters are stripped and controlled via API parameters; --quality / --q (1–4) is passed through.

Maximum string length: 2048

Example:

"A cinematic shot of a Maine Coon cat on a neon-lit balcony --ar 16:9 --s 500"

quality

enum<string>

default:standard

Output quality

standard: Standard resolution (default), 1x multiplier
hd: Native HD output, 1.5x multiplier. Mutually exclusive with speed: draft

Pricing note: the quality multiplier is combined (multiplied) with the speed multiplier.

Available options:

standard,

hd

model_params

object

Model parameters

Show child attributes

callback_url

string<uri>

HTTPS callback URL for task completion

Callback timing:

Triggered when the task is completed or failed
Sent after billing confirmation

Security restrictions:

HTTPS protocol only
Callbacks to private IP addresses are 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
Up to 3 retries after failure (retries at 1s/2s/4s after failure)
Callback response body format matches the task query endpoint
A 2xx status code is considered successful; other status codes trigger retries

Example:

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

Response

Task created successfully

created

integer

Task creation timestamp

Example:

1757165031

string

Task ID

Example:

"task-unified-1757165031-mjv82"

model

string

Actual model name used

Example:

"mj-v8.2"

object

enum<string>

Task object 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

Async task info

Show child attributes

type

enum<string>

Task output type

Available options:

text,

image,

audio,

video

Example:

"image"

usage

object

Usage and billing info

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

Midjourney V8.2 Image Generation

Authorizations

All endpoints require Bearer Token authentication

Body

Response