Wan 2.7 Image

Overview

Wan 2.7 Image is an Alibaba image model for text-to-image, image editing, and sequential image generation. Use this page when you are ready to call the API after trying the model in the APIXO playground.

Capability	Value
Model ID	`wan-2-7-image`
Modes	`omni-image`, `omni-image-pro`
Prompt	Required, non-empty; supports Chinese/English; max `5000` characters (model-side truncation)
Input images	Optional `image_urls`, `1-9` URLs when provided
Image limits (`image_urls`)	`JPEG/JPG/PNG(no alpha)/BMP/WEBP`, width/height `240-8000` px, ratio `1:8-8:1`, file size `<=20MB`
Resolution tiers	`1k`, `2k`, `4k`
4k availability	Only when `mode=omni-image-pro`, no `image_urls`, and `enable_sequential=false`
Output count (`num_images`)	`1-4` when `enable_sequential=false` (default `1`); `1-12` when `enable_sequential=true`
Interactive edit boxes	`bbox_list` requires `image_urls`; list length must match image count; each image supports up to `2` boxes
Color palette control	`color_palette` is available only when `enable_sequential=false`; `3-10` colors; ratio sum must be `100.00%`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/wan-2-7-image`	Submit a generation task
`GET`	`/statusTask/wan-2-7-image?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits a text-to-image task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-7-image" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "omni-image-pro",
      "prompt": "a cinematic panda walking through snow",
      "resolution": "2k",
      "num_images": 1
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/wan-2-7-image?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/image.png\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "InvalidParameter",
    "failMsg": "The parameter is invalid",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const imageUrls = payload.resultUrls;

Request body

Text-to-image

{
  "request_type": "async",
  "input": {
    "mode": "omni-image-pro",
    "prompt": "a cinematic panda walking through snow",
    "resolution": "4k",
    "num_images": 2,
    "enable_sequential": false,
    "watermark": false,
    "seed": 42
  }
}

Image editing

{
  "request_type": "callback",
  "callback_url": "https://your-server.com/webhooks/apixo",
  "input": {
    "mode": "omni-image",
    "image_urls": [
      "https://example.com/base.png",
      "https://example.com/style.png"
    ],
    "prompt": "blend the style naturally and keep lighting consistent",
    "resolution": "2k",
    "num_images": 1,
    "bbox_list": [
      [[120, 180, 360, 420]],
      []
    ]
  }
}

Parameters

request_type

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url

string

Required when request_type is callback. Must be a callback URL that can receive the final task payload. See Webhooks.

input

object

required

Wan 2.7 Image input parameters.

Show properties

mode

string

required

Generation mode. Supported values: omni-image, omni-image-pro.

prompt

string

required

Prompt text. Required for all requests and cannot be empty after trimming. Supports Chinese/English, maximum length is 5000 characters, and excess content is truncated by the model service.

image_urls

string[]

Optional image input list. When provided, must contain 1-9 image URLs. Image constraints: formats JPEG/JPG/PNG (no alpha), BMP, WEBP; width/height 240-8000 px; aspect ratio 1:8-8:1; file size <=20MB.

resolution

string

default:"2k"

Output resolution tier. Supported values: 1k, 2k, 4k. mode=omni-image does not support 4k. 4k is only available when mode=omni-image-pro, image_urls is empty, and enable_sequential=false.

num_images

integer

default:"1"

Requested output count. Accepts integer or numeric string input. Range is 1-4 when enable_sequential=false, and 1-12 when enable_sequential=true.

enable_sequential

boolean

default:"false"

Sequential/group generation switch. false (default) means normal generation. true enables sequential generation mode.

bbox_list

array[array[array[integer]]]

Optional interactive edit boxes. Requires image_urls. Structure is bbox_list[image_index][box_index] = [x1,y1,x2,y2]. The outer list length must equal image_urls length. Each image supports up to 2 boxes. Each box must contain exactly 4 integers and satisfy 0<=x1<x2 and 0<=y1<y2. Example: [[[120,180,360,420]], []].

color_palette

array

Optional custom color theme. Available only when enable_sequential=false. Must contain 3-10 colors. Each color object must include hex (#RRGGBB) and ratio (xx.xx%). All ratio values must sum to 100.00%.

negative_prompt

string

Optional negative prompt used to reduce unwanted visual elements.

watermark

boolean

default:"false"

Whether to add watermark. false (default) means no watermark. true adds a bottom-right watermark with fixed text AI 生成.

thinking_mode

boolean

default:"true (model-side)"

Thinking-mode switch. Effective only when enable_sequential=false and no input image is provided. When enabled, the model may improve complex prompt understanding, with additional latency.

seed

integer

Optional random seed. Supported range: 0-2147483647. A fixed seed improves reproducibility, but identical seeds do not guarantee identical outputs.

Response format

Submit task response

POST /generateTask/wan-2-7-image returns a task ID when the task is accepted:

code

integer

API status code. 200 means the task was accepted.

message

string

Human-readable status message.

data.taskId

string

Unique task identifier used with the status endpoint.

Status response fields

taskId

string

Unique task identifier.

state

string

Current task state: pending, processing, success, or failed.

resultJson

string

JSON string containing generated image URLs in resultUrls. Present when state is success.

failCode

string

Machine-readable failure code. Present when state is failed.

failMsg

string

Human-readable failure message. Present when state is failed.

createTime

integer

Task creation timestamp in Unix milliseconds.

completeTime

integer

Task completion timestamp in Unix milliseconds. Present after completion.

costTime

integer

Processing duration in milliseconds. Present after completion when provider timing is available.

If at least one image succeeds, the task can still return success, and resultJson.resultUrls contains only successful outputs.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-7-image" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "omni-image-pro",
      "prompt": "a premium product poster with soft studio light",
      "resolution": "2k",
      "num_images": 1
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Wan 2.7 Image is billed per generated image.

Mode	APIXO price
`omni-image`	`$0.03 / image`
`omni-image-pro`	`$0.075 / image`

Billing behavior:

precharge = requested_num_images * unit_price
final_charge = successful_images * unit_price
refund = precharge - final_charge (if partial failure)

For current public pricing, see Pricing. If this route is not listed there, backend billing follows ModelPricing.md.

Latency and polling

Wan 2.7 Image tasks are asynchronous. The backend does not provide a fixed public latency SLA; actual latency varies by prompt complexity, requested image count, image input fetch speed, and queue load.

Workflow	Recommended first poll	Poll interval
Text-only generation	10s after task creation	5s-10s
Image editing / multi-image input	10s-15s after task creation	5s-10s
Sequential generation (`enable_sequential=true`)	15s after task creation	8s-12s

For production workloads, use callback mode to avoid frequent polling.

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, parameter type, or value	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error	Retry with backoff
`502`	Third-party model service error	Retry with backoff
`504`	Third-party model timeout	Retry or use callback mode

Task failure codes

failCode is route-dependent and may come from mapped third-party model failures. Common values include:

Fail code	Meaning	What to do
`PromptInvalid`	Prompt is invalid or rejected by the model service	Rewrite the prompt and retry
`MissingParameter` / `BadRequest`	Required fields are missing or malformed	Check required fields and types
`SensitiveContentDetected` / `ProhibitedContentDetected`	Prompt or image input failed safety checks	Rewrite prompt or change input images
`RateLimitExceeded`	Model service or route rate limit was reached	Retry with backoff
`Task TimeOut` / `Timeout`	Generation did not finish in time	Retry or use callback mode

Parameter troubleshooting

mode must be omni-image or omni-image-pro.
prompt is required and cannot be empty.
resolution supports only 1k, 2k, 4k.
4k is invalid when mode=omni-image, when enable_sequential=true, or when image_urls is provided.
num_images range depends on enable_sequential: 1-4 when false, 1-12 when true.
image_urls supports 1-9 image URLs when provided.
bbox_list requires image_urls, its length must match image_urls, and each image supports at most 2 boxes.
color_palette is available only when enable_sequential=false, with 3-10 colors and total ratio 100.00%.

See Error Codes for the full error reference.

Documentation Index

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-image

​Image editing

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Task failure codes

​Parameter troubleshooting

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-image

Image editing

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Parameter troubleshooting

Related links