Wan 2.6 Video API

Overview

Wan 2.6 Video is an Alibaba video model for text-to-video, image-to-video, and reference-guided 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-2-6-video`
Modes	`text-to-video`, `image-to-video-flash`, `image-to-video`, `reference-to-video-flash`, `reference-to-video`
Prompt	Required for all modes, non-empty, max `1500` chars
Negative prompt	Optional, max `500` chars
Resolution tiers	`720p`, `1080p`
Duration	`text/image`: `2-15` seconds (default `5`); `reference`: `2-10` seconds (default `5`)
Prompt rewrite	`prompt_extend` optional boolean; `true` (default) enables rewrite, `false` disables rewrite
Image inputs	Exactly `1` URL for `image-to-video-flash` and `image-to-video`; `JPEG/JPG/PNG(no alpha)/BMP/WEBP`, `240-8000` px, `<=20MB`
Reference inputs	`1-5` URLs for `reference-to-video-flash` and `reference-to-video`; mixed image/video with `images<=5`, `videos<=3`, `images+videos<=5`
Audio input (`audio_urls`)	Optional `1` URL; `wav/mp3`, `3-30s`, `<=15MB`
Flash audio switch	`sound` is flash-only and defaults to `true`

Endpoint and authentication

Base URL:

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

Method	Endpoint	Purpose
`POST`	`/generateTask/wan-2-6-video`	Submit a generation task
`GET`	`/statusTask/wan-2-6-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

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

curl -X POST "https://api.apixo.ai/api/v1/generateTask/wan-2-6-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic fox walking through neon rain",
      "resolution": "720p",
      "duration": 5,
      "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-2-6-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": "PromptInvalid",
    "failMsg": "Prompt is invalid or rejected by provider",
    "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 cinematic fox walking through neon rain",
    "audio_urls": [
      "https://example.com/background.mp3"
    ],
    "negative_prompt": "blurry, low quality",
    "resolution": "1080p",
    "duration": 8,
    "prompt_extend": true,
    "shot_type": "multi",
    "seed": 42,
    "watermark": false
  }
}

Image-to-video-flash

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video-flash",
    "prompt": "make the character speak with subtle camera motion",
    "image_urls": [
      "https://example.com/hero.png"
    ],
    "audio_urls": [
      "https://example.com/voice.mp3"
    ],
    "resolution": "1080p",
    "duration": 5,
    "sound": true
  }
}

Reference-to-video

{
  "request_type": "async",
  "input": {
    "mode": "reference-to-video",
    "prompt": "character1 is reading a book in a cafe",
    "reference_urls": [
      "https://example.com/character1.png",
      "https://example.com/scene.mp4"
    ],
    "resolution": "720p",
    "duration": 6
  }
}

For non-flash modes, use image-to-video or reference-to-video and omit sound.

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 callback URL that can receive the final task payload. See Webhooks.

object

required

Wan 2.6 Video input parameters.

Show properties

string

required

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

string

required

Prompt text. Required for all modes and cannot be empty after trimming. Supports Chinese and English; maximum length is 1500 characters and excess content is truncated by the model service.

string

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

string[]

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

string[]

Required for reference-to-video-flash and reference-to-video. Must contain 1-5 URLs. Mixed image/video is supported with limits: images 0-5, videos 0-3, and total images + videos <= 5. Reference ordering maps to role order (character1, character2, …). Reference video constraints: mp4/mov, 1-30s, file size <= 100MB. Reference image constraints: JPEG/JPG/PNG (no alpha), BMP, WEBP, width/height 240-8000 px, file size <= 20MB.

string[]

Public audio input. Optional. If provided, must contain exactly one 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. In flash modes, when sound=false, audio input is ignored.

string

Output resolution tier. Supported values: 720p, 1080p. Defaults: text-to-video -> 720p; image-to-video and image-to-video-flash -> 720p; reference-to-video and reference-to-video-flash -> 1080p.

integer

default:"5"

Accepts integer or numeric string input. text-to-video, image-to-video-flash, and image-to-video: 2-15. reference-to-video-flash and reference-to-video: 2-10.

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

Optional shot mode. Supported values: single, multi. When both shot_type and prompt shot instructions are present, shot_type takes priority.

integer

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

boolean

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

boolean

default:"true (flash modes only)"

Flash-only audio generation switch for image-to-video-flash and reference-to-video-flash. true (default) generates voiced video. false generates silent video and ignores optional audio input.

Response format

Submit task response

POST /generateTask/wan-2-6-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 generated video URLs in resultUrls. 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 completion when provider timing is available.

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-2-6-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": "image-to-video-flash",
      "prompt": "make the character speak with subtle camera motion",
      "image_urls": [
        "https://example.com/hero.png"
      ],
      "resolution": "720p",
      "duration": 5,
      "sound": false
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Wan 2.6 Video is billed per second. Total cost is duration * unitPrice. Standard (non-flash) modes:

Mode	Resolution	APIXO official price
`text-to-video`	`720p`	`$0.10 / second`
`text-to-video`	`1080p`	`$0.15 / second`
`image-to-video`	`720p`	`$0.10 / second`
`image-to-video`	`1080p`	`$0.15 / second`
`reference-to-video`	`720p`	`$0.20 / second`
`reference-to-video`	`1080p`	`$0.30 / second`

Flash modes:

Mode	Resolution	`sound=false`	`sound=true`
`image-to-video-flash`	`720p`	`$0.025 / second`	`$0.05 / second`
`image-to-video-flash`	`1080p`	`$0.0375 / second`	`$0.075 / second`
`reference-to-video-flash`	`720p`	`$0.05 / second`	`$0.10 / second`
`reference-to-video-flash`	`1080p`	`$0.08 / second`	`$0.16 / second`

For current route and market comparison pricing, see Pricing.

Latency and polling

Wan 2.6 Video tasks are asynchronous. The backend does not provide a fixed public latency SLA; actual latency varies by mode, duration, resolution, prompt complexity, media fetch speed, and provider queue load.

Workflow	Recommended first poll	Poll interval
`text-to-video`	30s after task creation	10s
`image-to-video` / `image-to-video-flash`	30s after task creation	10s
`reference-to-video` / `reference-to-video-flash`	45s after task creation	10s-15s

For production workloads, use callback mode to avoid frequent polling on long-running video jobs.

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 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`	Model provider error	Retry with backoff
`504`	Model provider 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 mode-specific required fields
`SensitiveContent` / `SensitiveContentDetected`	Prompt or media failed safety checks	Change prompt or media
`RateLimitExceeded`	Model service or route rate limit was reached	Retry with exponential backoff
`Task TimeOut` / `Timeout`	Model generation timed out	Retry or use callback mode

Parameter troubleshooting

prompt is required and must be non-empty for all modes.
image-to-video-flash and image-to-video require exactly one image_urls item.
reference-to-video-flash and reference-to-video require reference_urls with 1-5 items.
sound is valid only for flash modes.
duration defaults to 5, but reference modes only allow up to 10.
In flash modes, when sound=false, optional audio input is ignored.

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-flash

​Reference-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-flash

Reference-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