Wan 2.5 Video API

Overview

Wan 2.5 generates short videos from a text prompt or from one reference image plus a prompt.

Capability	Value
Model ID	`wan-2-5-video`
Modes	`text-to-video`, `image-to-video`
Prompt	Max `1500` characters (`text-to-video` required and non-empty, `image-to-video` optional)
Negative prompt	Optional, max `500` characters
Reference images	`image-to-video` requires exactly 1 URL; `JPEG/JPG/PNG(no alpha)/BMP/WEBP`, width and height `240-8000` px, file size `<=20MB`
Audio input	`audio_urls` optional with exactly 1 URL; `wav/mp3`, `3-30s`, file size `<=15MB`
Resolutions	`480p`, `720p`, `1080p`
Duration	`5` or `10` seconds
Prompt rewrite	`prompt_extend` optional boolean; `true` (default) enables rewrite, `false` disables rewrite
Text-to-video aspect ratios	`16:9`, `9:16`, `1:1` (all resolutions), plus `4:3`, `3:4` for `720p`/`1080p`

Endpoint and authentication

Base URL:

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

Method	Endpoint	Purpose
`POST`	`/generateTask/wan-2-5-video`	Submit a generation task
`GET`	`/statusTask/wan-2-5-video?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

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-5-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic shot of clouds drifting over a quiet mountain lake",
      "audio_urls": [
        "https://example.com/music.mp3"
      ],
      "resolution": "720p",
      "duration": 5,
      "aspect_ratio": "16:9",
      "prompt_extend": true
    }
  }'

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-video?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/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965752317,
    "costTime": 141388
  }
}

Failed response:

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

Parse resultJson after state becomes success:

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

Request body

Text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "text-to-video",
    "prompt": "a serene mountain landscape with moving clouds and gentle breeze",
    "audio_urls": [
      "https://example.com/music.mp3"
    ],
    "resolution": "480p",
    "duration": 5,
    "aspect_ratio": "1:1",
    "prompt_extend": true,
    "negative_prompt": "low quality, blurry",
    "watermark": false,
    "seed": 20260413
  }
}

Image-to-video

{
  "request_type": "callback",
  "callback_url": "https://your-server.com/webhooks/apixo",
  "input": {
    "mode": "image-to-video",
    "image_urls": [
      "https://example.com/reference.png"
    ],
    "prompt": "turn this photo into a smooth cinematic shot with a slow push-in camera move",
    "audio_urls": [
      "https://example.com/music.mp3"
    ],
    "resolution": "1080p",
    "duration": 10
  }
}

Parameters

string

default:"async"

required

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

string

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

object

required

Wan 2.5 input parameters.

Show properties

string

required

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

string

Prompt text. Required for text-to-video; optional for image-to-video. Supports Chinese and English; maximum length is 1500 characters.

string[]

Reference image URL list. Required for image-to-video. Must contain exactly 1 URL. Image constraints: formats JPEG/JPG/PNG (no alpha), BMP, WEBP; width and height 240-8000 px; file size <= 20MB.

string[]

Optional audio URL list. Supports exactly 1 URL. Audio constraints: formats wav/mp3, duration 3-30s, file size <= 15MB. If audio is longer than duration, only the first duration seconds are used; if audio is shorter than output video duration, the remaining segment is silent.

string

default:"1080p"

Output resolution. Supported values: 480p, 720p, 1080p.

integer

default:"5"

Output duration in seconds. Supported values: 5, 10.

boolean

default:"true"

Whether to enable prompt rewriting before generation. true (default) enables rewriting and can improve short prompts but may increase latency. false disables rewriting.

string

default:"16:9"

Text-to-video only. 480p supports 16:9, 9:16, 1:1; 720p and 1080p support 16:9, 9:16, 1:1, 4:3, 3:4.

string

Optional negative prompt describing what to avoid. Supports Chinese and English; maximum length is 500 characters.

boolean

Optional watermark switch. false (default) means no watermark. true adds a bottom-right watermark with fixed text AI 生成.

integer

Optional random seed in [0, 2147483647]. A fixed seed improves reproducibility, but identical seeds do not guarantee identical outputs.

Response format

Submit task response

POST /generateTask/wan-2-5-video returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

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

string

JSON string containing the generated video URLs. Present when state is success.

string

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

string

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

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds. Present after successful completion.

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-video" \
  -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": "text-to-video",
      "prompt": "a polished product demo video with gentle camera movement",
      "resolution": "720p",
      "duration": 5,
      "aspect_ratio": "16:9"
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Wan 2.5 is billed per generated second.

Mode	Resolution	Unit price
`text-to-video`	`480p`	`$0.05 / second`
`text-to-video`	`720p`	`$0.10 / second`
`text-to-video`	`1080p`	`$0.15 / second`
`image-to-video`	`480p`	`$0.05 / second`
`image-to-video`	`720p`	`$0.10 / second`
`image-to-video`	`1080p`	`$0.15 / second`

Final cost formula:

total_cost = duration_seconds * resolution_unit_price

For current route and market comparison pricing, see Pricing.

Latency and polling

Video generation is long-running. Actual latency may vary by prompt complexity, mode, selected resolution, and current queue load.

Request shape	Typical generation time	Recommended first poll	Poll interval
`480p`	40s-120s	40s after task creation	10s
`720p`	60s-180s	60s after task creation	10s
`1080p`	90s-250s	90s after task creation	10s

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

Practical notes:

Use aspect_ratio only with text-to-video.
audio_urls supports one MP3/WAV URL with max 15 MB; recommended duration range is 3-30 seconds.
For image-to-video, image_urls must contain exactly one image URL and the image file should be at most 20 MB.
Result URLs are temporary. Download important outputs promptly.

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, mode, parameter, or media URL shape	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 account cannot access the model	Check account permissions
`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 for long-running jobs

Task failure codes

Fail code	Meaning	What to do
`CONTENT_VIOLATION`	Prompt or reference image failed safety checks	Change the prompt or input image
`INVALID_IMAGE_URL`	A reference image URL could not be fetched or decoded	Use a public, direct media URL
`INVALID_PARAMETER`	A model parameter is unsupported or malformed	Check `mode`, `resolution`, `duration`, `aspect_ratio`, `image_urls`, and `audio_urls`
`INSUFFICIENT_BALANCE`	The account does not have enough balance for the task	Add balance before retrying
`TIMEOUT`	Generation did not finish in time	Retry, reduce input complexity, or use callback mode

Parameter troubleshooting

prompt is required for text-to-video, optional for image-to-video.
image_urls is required only for image-to-video and must contain exactly one URL.
audio_urls supports exactly one MP3/WAV URL when provided; file size should be ≤ 15 MB and recommended duration range is 3-30 seconds.
resolution defaults to 1080p when omitted.
duration defaults to 5 when omitted and only accepts 5 or 10.
aspect_ratio applies only to text-to-video.

See Error Codes for the full error reference.

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-video

​Image-to-video

​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-video

Image-to-video

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