Wan 2.5 API documentation

Integrate Wan 2.5 with your VezAPI key. The operations below share the same authentication and account balance.

Base URL: https://api.vezapi.com
Send Authorization: Bearer YOUR_VEZAPI_KEY. Use a unique Idempotency-Key for each submission; reuse it only when checking the same request.

Wan 2.5 - Image to Video

POST/api/v1/jobs/createTask

Model IDs: wan/2-5-image-to-video

Parameter	Type	Description & constraints
`model` required	`string`	The model name used for generation. This field is required. - This endpoint must use the `wan/2-5-image-to-video` model Values: `"wan/2-5-image-to-video"` Default: `"wan/2-5-image-to-video"`
`callBackUrl` optional	`string`	Callback URL for task completion notifications. Optional parameter. If provided, the system will send a POST request to this URL when the task completes, whether it succeeds or fails. If omitted, no callback notification will be sent.
`input` required	`object`	Input parameters for the image-to-video task.
`input.prompt` required	`string`	The text prompt describing the desired video motion. Maximum length: 800 characters. `maxLength: 800`
`input.image_url` required	`string`	URL of the image to use as the first frame. Must be publicly accessible. - Please provide the URL of the uploaded file, not raw file content - Accepted types: `image/jpeg`, `image/png`, `image/webp` - Max size: 10.0MB
`input.duration` required	`string`	The duration of the generated video in seconds. - `5`: 5 seconds - `10`: 10 seconds Values: `"5", "10"`
`input.resolution` required	`string`	Required. 720p or 1080p. Values: `"720p", "1080p"`
`input.negative_prompt` optional	`string`	Negative prompt used to describe content to avoid. Maximum length: 500 characters. `maxLength: 500`
`input.enable_prompt_expansion` optional	`boolean`	Whether to enable prompt rewriting using LLM. - Boolean value: `true` / `false`
`input.seed` optional	`integer`	Random seed for reproducibility. If omitted, a random seed is chosen.
`input.nsfw_checker` optional	`boolean`	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

Request example

curl -X POST 'https://api.vezapi.com/api/v1/jobs/createTask' \
  -H 'Authorization: Bearer YOUR_VEZAPI_KEY' \
  -H 'Idempotency-Key: your-unique-request-id' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "wan/2-5-image-to-video",
  "input": {
    "prompt": "The same woman from the reference image looks directly into the camera, takes a breath, then smiles brightly and speaks with enthusiasm: \"Have you heard? Alibaba Wan 2.5 API is now available on Kie.ai!\" Ambient audio: quiet indoor atmosphere, soft natural room tone. Camera: medium close-up, steady framing, natural daylight mood, accurate lip-sync with dialogue.",
    "image_url": "https://example.com/input.png",
    "duration": "5",
    "resolution": "1080p"
  }
}'

Responses and errors

HTTP 200

Request successful

Parameter	Type	Description & constraints
`code` optional	`integer`	Status code of the request. The HTTP status is 200 even when the request fails, so always check this field: 200 means success; any other value means the request failed and msg describes the reason. Common values: 401 invalid or missing API key; 402 insufficient credits; 429 rate limit exceeded; 422 or 500 the request could not be processed (read msg and check your parameters before retrying). Values: `200, 401, 402, 404, 422, 429, 433, 455, 500, 501, 505`
`msg` optional	`string`	Response message, error description upon failure
`data` required	`object`
`data.taskId` required	`string`	The task ID can be used with the "Get Task Details" endpoint to query the task status.

HTTP 500

Server error.

Wan 2.5 - Text to Video

POST/api/v1/jobs/createTask

Model IDs: wan/2-5-text-to-video

Parameter	Type	Description & constraints
`model` required	`string`	The model name used for generation. This field is required. - This endpoint must use the `wan/2-5-text-to-video` model Values: `"wan/2-5-text-to-video"` Default: `"wan/2-5-text-to-video"`
`callBackUrl` optional	`string`	Callback URL for task completion notifications. Optional parameter. If provided, the system will send a POST request to this URL when the task completes, whether it succeeds or fails. If omitted, no callback notification will be sent.
`input` required	`object`	Input parameters for the text-to-video task.
`input.prompt` required	`string`	The text prompt for video generation. Supports Chinese and English. Maximum length: 800 characters. `maxLength: 800`
`input.duration` required	`string`	The duration of the generated video in seconds. - `5`: 5 seconds - `10`: 10 seconds Values: `"5", "10"`
`input.aspect_ratio` optional	`string`	The aspect ratio of the generated video. - `16:9`: Landscape - `9:16`: Portrait - `1:1`: Square Values: `"16:9", "9:16", "1:1"`
`input.resolution` required	`string`	Required. 720p or 1080p. Values: `"720p", "1080p"`
`input.negative_prompt` optional	`string`	Negative prompt used to describe content to avoid. Maximum length: 500 characters. `maxLength: 500`
`input.enable_prompt_expansion` optional	`boolean`	Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time. - Boolean value: `true` / `false`
`input.seed` optional	`integer`	Random seed for reproducibility. If omitted, a random seed is chosen.
`input.nsfw_checker` optional	`boolean`	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

Request example

curl -X POST 'https://api.vezapi.com/api/v1/jobs/createTask' \
  -H 'Authorization: Bearer YOUR_VEZAPI_KEY' \
  -H 'Idempotency-Key: your-unique-request-id' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "wan/2-5-text-to-video",
  "input": {
    "prompt": "A dimly lit jazz bar at night, wooden tables glowing under warm pendant lights. Patrons sip drinks and chat quietly while a three-piece band performs on stage. The saxophone player stands under a spotlight, gleaming instrument reflecting the light. No dialogue. Ambient audio: smooth live jazz music with saxophone and piano, clinking glasses, low murmur of audience conversations, occasional burst of laughter from a nearby table. Camera: slow pan across the crowd, then gentle zoom toward the saxophone player'\''s solo, focusing on expressive hand movements.",
    "duration": "5",
    "aspect_ratio": "16:9",
    "resolution": "1080p"
  }
}'

Responses and errors

HTTP 200

Request successful

Parameter	Type	Description & constraints
`code` optional	`integer`	Status code of the request. The HTTP status is 200 even when the request fails, so always check this field: 200 means success; any other value means the request failed and msg describes the reason. Common values: 401 invalid or missing API key; 402 insufficient credits; 429 rate limit exceeded; 422 or 500 the request could not be processed (read msg and check your parameters before retrying). Values: `200, 401, 402, 404, 422, 429, 433, 455, 500, 501, 505`
`msg` optional	`string`	Response message, error description upon failure
`data` required	`object`
`data.taskId` required	`string`	The task ID can be used with the "Get Task Details" endpoint to query the task status.

HTTP 500

Server error.

Task status and callbacks

For asynchronous tasks, keep the returned taskId. Query GET /api/v1/jobs/recordInfo?taskId=... or provide callBackUrl when creating the task. Only the account that created a task can access it or derive new resources from it.

A timeout can mean the submission was accepted. Inspect the existing request in your dashboard; do not create another task automatically. Callback delivery is retried and may arrive more than once. Deduplicate with X-VezAPI-Event-Id.

Files, logs and billing

Generated media normally follows a 14-day provider lifetime; uploaded files expire after 24 hours. Save the files you need before expiration. VezAPI streams registered files without keeping a permanent media library. Request logs are retained for two calendar months.

Credits are reserved before submission. Final deductions match actual discounted consumption one for one. Unknown usage pauses new paid requests. If available funds cannot cover final usage while protecting other reservations, settlement stays pending until funded; model usage cannot make the wallet negative. Time-based inputs require server-side metadata reads; a failed read prevents submission.