VidMage

VidMage is an AI video and image creation platform for creators. Turn your ideas and images into videos and fresh visuals.

Open the creator tools
Explore APIs
AI Video APIsAI Image APIsAI Audio APIsAI 3D APIsAI Face Swap APIsAI Effects APIs
Build with VidMage
QuickstartAPI keysVidMage MCPError reference
Your account
Developer consoleAbout VidMagePlans and creditsAPI billingContact support
© 2026 VidMage. All rights reserved.
Privacy PolicyTerms of ServiceReport Abuse
Skip to content
VidMage/Developers
Overview
APIs
All APIsAI Video APIsAI Image APIsAI Audio APIsAI 3D APIsAI Face Swap APIsAI Effects APIs
DocumentationVidMage MCPOpen console
Developers/Documentation/Wan AI Video Generator API documentation
Start here
DocumentationQuickstartAuthentication
Core workflows
File uploadsTask lifecycleCredits and billingErrors and recoveryVidMage MCP
Browse documentation
All API documentation
Video documentation 36AI Video Head SwapAI Video Face SwapAI Multiple Face Swap VideoAI Text to VideoAI Image to VideoAI Video to VideoAI Video ExtenderAI Video to Anime ConverterAI Video Background RemoverAI Video Watermark RemoverSora Link Watermark RemoverSora 2 Video GeneratorAI Photo DanceAI Motion ControlAI Talking PhotoAI Lip SyncAI Subtitle GeneratorAI Video UpscalerKling AI Video GeneratorPixVerse AI Video GeneratorHailuo AI Video GeneratorMiniMax H3 AI Video GeneratorGrok Video GeneratorSora 2 AI Video GeneratorWan AI Video GeneratorWan 3.0 AI Video GeneratorSeedance 2.0 AI Video GeneratorSeedance 2.5 AI Video GeneratorSeedance AI Video GeneratorMidjourney Video GeneratorVidu AI Video GeneratorVeo 3.1 AI Video GeneratorKling 3.0 AI Video GeneratorSkyReels AI Video GeneratorHappyHorse AI ModelRunway AI Video Generator
Image documentation 24AI Photo Face SwapAI Head SwapAI Multiple Face SwapAI Text to ImageAI Image to ImageAI Girl GeneratorAI Hairstyle ChangerAI Clothes ChangerAI Object RemoverAI Image Watermark RemoverAI Image UpscalerGPT Image 2 Image to ImageAI GIF Face SwapMidjourney AI Image GeneratorGrok AI Image GeneratorNano Banana AI Image GeneratorGPT Image GeneratorSeedream AI Image GeneratorZ-Image AI ModelWan Image GeneratorQwen Image GeneratorQwen 3.0 Image GeneratorGPT Image 2 GeneratorGPT Image 2.5 Generator
Audio documentation 3AI Voice CloneAI Voice DesignAI Text to Music
3d documentation 3AI Image to 3DAI Four-View to 3DAI Text to 3D

Wan AI Video Generator API documentation

Generate videos with Wan AI Video Generator (Alibaba). Supports both text and image input modes. The reference mode accepts image, video, audio inputs.

On this page01 / 09
01Endpoints02Parameters and input rules03text to video04image to video05multimodal video06Example request07Task results and recovery08Credits09Integration guides

Endpoints

Contract itemValue
Capabilitywan-ai-video-generator
SubmitPOST https://vidmage.ai/api/v1/wan-ai-video-generator/submit
QueryPOST https://vidmage.ai/api/v1/wan-ai-video-generator/query
Task identifiertaskId
Result fieldvideoUrl

Authenticate with Authorization: Bearer YOUR_API_KEY. Save the task identifier and query the same capability. Use a stable Idempotency-Key for submission retries.

Product guide: Wan Video API

Parameters and input rules

FieldTypeRequiredDefaultMeaning and limits
promptstringNoNot specifiedText prompt describing the video to generate (max 5000 chars). Optional only in provider modes whose image input fully defines the generation.
Maximum characters: 5000
imageUrlstringNoNot specifiedOptional input image URL. When provided, the task runs in image-to-video mode. In that mode, output ratio is inferred from the input image.
imageUrlsstring[]NoNot specifiedOptional multimodal reference images. Public URLs only; images and videos together are limited to 5.
Maximum items: 5
videoUrlsstring[]NoNot specifiedOptional multimodal reference videos. Images and videos together are limited to 5.
Maximum items: 5
audioUrlsstring[]NoNot specifiedOptional multimodal reference audio..
Maximum items: 1
lastFrameUrlstringNoNot specifiedOptional public URL for the final frame in image-to-video mode.
durationstringNo"5"Video duration in seconds.
Values: "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"
aspectRatiostringNo"16:9"Output aspect ratio for modes that expose a ratio parameter. Ignored when imageUrl selects a mode whose ratio is inferred from the input image.
Values: "16:9", "9:16", "1:1", "4:3", "3:4"
resolutionstringNo"720p"Output resolution tier.
Values: "720p", "1080p"
audioUrlstringNoNot specifiedOptional background music or audio track.
negativePromptstringNoNot specifiedDescribe unwanted video content or artifacts.
Minimum characters: 0
Maximum characters: 500
promptExtendbooleanNotrueRewrite and enrich the prompt automatically.
seedintegerNoNot specifiedRandom seed; leave unset for a random result.
Minimum: 0
Maximum: 2147483647
Multiple of: 1

Images and videos together may contain at most 5 references.

text to video

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

ControlMode-specific rule
promptRequired; 1–5000 characters.
durationJSON string. Values: "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15". Default: 5.
aspectRatioValues: "16:9", "9:16", "1:1", "4:3", "3:4". Default: 16:9.
resolutionValues: "720p", "1080p". Default: 720p.
audioUrlOptional background music or audio track.
negativePromptDescribe unwanted video content or artifacts.
Minimum characters: 0
Maximum characters: 500
promptExtendRewrite and enrich the prompt automatically.
Default: true
seedRandom seed; leave unset for a random result.
Minimum: 0
Maximum: 2147483647
Multiple of: 1

image to video

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

ControlMode-specific rule
promptOptional; 0–5000 characters.
durationJSON string. Values: "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15". Default: 5.
aspectRatioNot used in this mode.
resolutionValues: "720p", "1080p". Default: 720p.
imageUrlFormats: jpg, jpeg, png, bmp, webp.
lastFrameUrlOptional final-frame image.
audioUrlOptional background music or audio track.
negativePromptDescribe unwanted video content or artifacts.
Minimum characters: 0
Maximum characters: 500
promptExtendRewrite and enrich the prompt automatically.
Default: true
seedRandom seed; leave unset for a random result.
Minimum: 0
Maximum: 2147483647
Multiple of: 1

multimodal video

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

ControlMode-specific rule
promptRequired; 1–5000 characters.
durationJSON string. Values: "2", "3", "4", "5", "6", "7", "8", "9", "10". Default: 5.
aspectRatioValues: "16:9", "9:16", "1:1", "4:3", "3:4". Default: 16:9.
resolutionValues: "720p", "1080p". Default: 1080p.
imageUrlsUp to 5 files. Formats: jpg, jpeg, png, bmp, webp.
videoUrlsUp to 5 files. Formats: mp4, mov.
audioUrlsUp to 1 files. Formats: mp3, wav.
ReferencesAt least one reference input is required.
Combined referencesImages and videos together: maximum 5.
negativePromptDescribe unwanted video content or artifacts.
Minimum characters: 0
Maximum characters: 500
promptExtendRewrite and enrich the prompt automatically.
Default: true
seedRandom seed; leave unset for a random result.
Minimum: 0
Maximum: 2147483647
Multiple of: 1

Example request

{
  "prompt": "A slow crane shot rises above an ancient riverside town as lanterns illuminate the evening mist",
  "duration": "5",
  "aspectRatio": "16:9",
  "resolution": "720p",
  "promptExtend": true
}
# Set VIDMAGE_IDEMPOTENCY_KEY to a unique value for this task; preserve it for transport retries.
curl -X POST "https://vidmage.ai/api/v1/wan-ai-video-generator/submit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Idempotency-Key: ${VIDMAGE_IDEMPOTENCY_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A slow crane shot rises above an ancient riverside town as lanterns illuminate the evening mist","duration":"5","aspectRatio":"16:9","resolution":"720p","promptExtend":true}'
# -> { "success": true, "taskId": "...", "creditsConsumed": ... }

Task results and recovery

URL of the generated video. Read videoUrl from the completed query response. Preserve taskId while the task is running.

curl -X POST "https://vidmage.ai/api/v1/wan-ai-video-generator/query" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "TASK_ID_FROM_SUBMIT" }'
# -> { "success": true, "data": { "status": "...", "videoUrl": "https://..." } }

Submission and task queries report the available task and usage information. A timeout is not a confirmed failure. Recover the existing task instead of resubmitting.

For face selection and error recovery, follow Task lifecycle. MCP uses the normalized taskId argument in get_task_result, including capabilities whose REST identifier is requestId.

Credits

Component / optionRateMinimum
720p15 credits / second—
1080p30 credits / second—

Base charge = duration × the selected resolution rate.

Use the Playground or the MCP credit estimator for your exact inputs. Credits and billing.

Integration guides

Authentication · File uploads · Task lifecycle · Error recovery · MCP

Reference generated from the current API contractDocumentation home ↗