Wan 2.5 Image API

Wan 2.5 Image API for text-to-image and image-to-image generation with up to four outputs per task

Overview

Wan 2.5 Image is an Alibaba image model for text-to-image and image-to-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-2-5-image
Modes	text-to-image, image-to-image
Prompt	Required, non-empty; supports Chinese/English; max 2000 characters (model-side truncation)
Negative prompt	Optional; supports Chinese/English; max 500 characters (model-side truncation)
Images per task	num_images supports 1-4, default 4
Reference images	image-to-image requires 1-3 image URLs
Input image limits (image_urls)	JPEG/JPG/PNG(no alpha)/BMP/WEBP, width/height 384-5000 px, file size <=10MB
Aspect ratios (text-to-image)	1:1, 3:4, 4:3, 9:16, 16:9
Aspect ratios (image-to-image)	1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9

Endpoint and authentication

Base URL:

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

Method	Endpoint	Purpose
POST	/generateTask/wan-2-5-image	Submit a generation task
GET	/statusTask/wan-2-5-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-2-5-image" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-image",
      "prompt": "a cinematic panda in snow",
      "aspect_ratio": "1:1",
      "num_images": 4
    }
  }'

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-2-5-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/img1.png\",\"https://file.apixo.ai/img2.png\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "PromptInvalid",
    "failMsg": "Prompt is invalid or rejected by the model service",
    "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": "text-to-image",
    "prompt": "a cinematic panda in snow",
    "negative_prompt": "blurry, low quality",
    "aspect_ratio": "16:9",
    "num_images": 4
  }
}

Image-to-image

{
  "request_type": "async",
  "input": {
    "mode": "image-to-image",
    "prompt": "merge style of image 2 into image 1 and keep image 3 color mood",
    "negative_prompt": "low quality",
    "aspect_ratio": "3:4",
    "num_images": 3,
    "image_urls": [
      "https://example.com/base.png",
      "https://example.com/style.png",
      "https://example.com/color.png"
    ]
  }
}

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 2.5 Image input parameters.

Show properties

mode · string · required

Generation mode. Supported values: text-to-image, image-to-image.

prompt · string · required

Prompt text. Required for both modes and cannot be empty after trimming. Supports Chinese and English, maximum length is 2000 characters, and excess content is truncated by the model service.

negative_prompt · string

Optional negative prompt. Supports Chinese and English, maximum length is 500 characters, and excess content is truncated by the model service.

aspect_ratio · string · default: "1:1"

Output aspect ratio. text-to-image: 1:1, 3:4, 4:3, 9:16, 16:9. image-to-image: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9.

num_images · integer · default: "4"

Number of images requested. Supports 1-4. Accepts integer input (numeric strings are also accepted).

image_urls · string[]

Required for image-to-image. Must contain 1-3 image URLs. Image constraints: formats JPEG/JPG/PNG (no alpha), BMP, WEBP; width and height 384-5000 px; file size <=10MB. Ignored in text-to-image.

Response format

Submit task response

POST /generateTask/wan-2-5-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 includes only successful images.

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-2-5-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": "image-to-image",
      "prompt": "turn this into a cinematic movie still",
      "aspect_ratio": "16:9",
      "num_images": 2,
      "image_urls": [
        "https://example.com/source-1.png"
      ]
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Wan 2.5 Image is billed per generated image.

Mode	APIXO price
text-to-image	$0.03 / image
image-to-image	$0.03 / image

Billing behavior:

precharge = requested_num_images * unit_price_for_mode
final_charge = successful_images * unit_price_for_mode
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 2.5 Image tasks are asynchronous. The backend does not provide a fixed public latency SLA; actual latency varies by prompt complexity, requested image count, media fetch speed, and queue load.

Workflow	Recommended first poll	Poll interval
text-to-image	10s after task creation	5s-10s
image-to-image	10s-15s after task creation	5s-10s

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 for the selected mode
SensitiveContentDetected / ProhibitedContentDetected	Prompt or media 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

• prompt is required for both modes and cannot be empty.
• image_urls is required only for image-to-image, and must contain 1-3 items.
• num_images supports 1-4; if omitted, default is 4.
• aspect_ratio must match the selected mode’s supported set.
• aspect_ratio defaults to 1:1 when omitted.
• In text-to-image, any provided image_urls input is ignored.

See Error Codes for the full error reference.

Related links

• Generation API Overview
• Image Models
• Generate Task
• Status Task
• Webhooks
• Error Codes
• Parameter Specification
• Try Wan 2.5 Image in the APIXO Playground
• Pricing