Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No video yet. Submit the form to generate video.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
wan 2.6,video to video,10s-1080p videowanduration: 10, resolution: 1080p, nsfw_checker: false | Starter | 5per run | $0.023 | - | - |
wan 2.6,video to video,10s-720p videowanduration: 10, resolution: 720p, nsfw_checker: false | Starter | 5per run | $0.023 | - | - |
wan 2.6,video to video,15s-1080p videowanduration: 15, resolution: 1080p, nsfw_checker: false | Starter | 5per run | $0.023 | - | - |
wan 2.6,video to video,15s-720p videowanduration: 15, resolution: 720p, nsfw_checker: false | Starter | 5per run | $0.023 | - | - |
wan 2.6,video to video,5s-1080p videowanduration: 5, resolution: 1080p, nsfw_checker: false | Starter | 5per run | $0.023 | - | - |
wan 2.6,video to video,5s-720p videowanduration: 5, resolution: 720p, nsfw_checker: false | Starter | 5per run | $0.023 | - | - |
Competitor pricing costs $136.364/day more
ApiPass is 27.27% lower, estimated at Based on 1,000 videos/day
wan 2.6,video to video,5s-720p
duration: 5, resolution: 720p, nsfw_checker: false
ApiPass Price
$0.364
80 credits per run
Competitor Prices
Complete guide to using wan 2.6 video to video
Use uploaded reference videos to guide the generation of new scenes.
Developed within the Alibaba ecosystem, Wan 2.6 is a cutting-edge AI video generation model designed to turn simple prompts and reference media into cohesive, multi-shot stories. Available seamlessly through APIPASS, the Wan 2.6 Video-to-Video (Reference-to-Video) API empowers developers to use an uploaded reference clip to guide the creation of brand new scenes . The API intelligently extracts core visual and auditory elements—such as a subject's appearance, overall style, and voice—and applies them consistently to newly generated content. This allows you to output high-definition, 1080p cinematic videos up to 15 seconds in length, complete with native audio and precise lip-sync, making it the perfect commercial-grade solution for your applications.
Provide a prompt plus one or more source videos to transform the original footage into a new motion, style, or scene interpretation while preserving the underlying timing and structure.
The upstream API supports up to 3 video URLs per request. The adapter accepts video_urls directly and also normalizes video and video_url aliases into the same field.
Wan 2.6 video-to-video currently supports only 5-second and 10-second outputs. The adapter normalizes unsupported values back to 5 seconds.
Leverage our advanced storytelling engine to generate 1080p videos featuring smooth scene transitions, balanced pacing, and natural camera movement. Through Wan 2.6 API, you can easily translate storyboard-style prompts into fully connected visual narratives.
Build character-driven stories with perfect continuity. The Wan 2.6 Video to Video API allows you to extract precise appearance, motion styles, and vocal characteristics from a reference clip, guaranteeing stable identities across all generated scenes.
Extend your creative narratives with video outputs of up to 15 seconds. The Wan 2.6 Video to Video API ensures your generations maintain flawless frame-to-frame consistency, keeping complex details like lighting, environmental elements, and character outfits perfectly stable in motion.
Deliver publish-ready, high-fidelity content by combining dynamic camera actions—like pans, zooms, and tracking shots—with fully integrated native audio. TheWan 2.6 Video to Video API seamlessly generates synchronized background music, ambient sound, and accurate lip-sync dialogue in a single workflow.
The integration flow follows the same asynchronous jobs API used by the other Kie-backed models.
Choose wan/wan-2-6-video-to-video as the model and prepare the input object with prompt, video_urls, and any optional controls such as duration, resolution, and nsfw_checker.
Send the payload to the ApiPass /api/v1/jobs/createTask endpoint. The adapter maps the public model name to the upstream Kie.ai identifier and returns a taskId when the request is accepted.
Track the task through the query endpoint or your callback URL. The adapter maps upstream task states into ApiPass states such as queuing, generating, success, and fail.
After the task succeeds, read resultUrls from the task result object. For completed tasks, the adapter attempts to return CDN-backed URLs when the upload step succeeds.
These suggestions follow the request constraints implemented by the adapter and documented by the provider.
Describe what should change in the source video rather than rewriting the whole scene abstractly. Wan 2.6 keeps the source timing and structure, so precise action and style instructions usually perform better.
Kie.ai documents support for MP4, QuickTime, and Matroska, with a maximum file size of 10MB per file and at most 3 video URLs. Staying within those limits avoids upstream validation failures.
Use 5 seconds for faster iteration and 10 seconds only when the motion needs extra time to read clearly. Prefer 720p for lower-cost experimentation and 1080p when final clarity matters.
Convert existing clips into new visual moods, wardrobe changes, dance variations, or ad-style edits while keeping the original movement rhythm.
Reuse a single base video across multiple prompt variants to test different themes, product angles, or stylistic directions in a consistent motion layout.
Teams can rapidly explore motion, dance, and styling changes on an existing clip before committing to a more expensive manual edit or larger video pipeline.
The document uses wan/wan-2-6-video-to-video as the public ApiPass model name because that is the current value in SUPPORT_MODEL after your update.
The readme and API sections explain that ApiPass forwards the public model to the upstream Kie.ai identifier wan/2-6-video-to-video, matching the adapter mapping logic.
The create-task API section documents the public ApiPass payload shape of model plus optional callBackUrl and input. That is the same shape the adapter receives before sending the request upstream.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Create a new Wan 2.6 video-to-video task through the ApiPass unified jobs API
ApiPass keeps the public request envelope stable across async video models. Wan-specific parameters are placed inside the input object.
1{
2 "model": "wan/wan-2-6-video-to-video",
3 "callBackUrl": "string (optional)",
4 "input": {
5 "prompt": "string",
6 "video_urls": [
7 "string"
8 ],
9 "duration": "5 | 10",
10 "resolution": "720p | 1080p",
11 "nsfw_checker": false
12 },
13 "channel": "auto"
14}modelRequiredstringThe public ApiPass model name for Wan 2.6 video-to-video.
"wan/wan-2-6-video-to-video"
callBackUrlOptionalstringOptional callback URL for task completion notifications.
"https://your-domain.com/api/callback"
channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
The input object contains the Wan 2.6 video-to-video parameters accepted by ApiPass. The adapter reshapes and normalizes them before forwarding the request upstream.
input.promptRequiredstringPrompt used to describe how the source video should be transformed.
"The video drinks milk tea while doing some improvised dance moves to the music."
input.video_urlsRequiredarray(URL)Source video URLs for the task. The adapter also accepts video and video_url and converts them to video_urls. Kie.ai supports at most 3 URLs.
["https://static.aiquickdraw.com/tools/example/1765957777782_cNJpvhRx.mp4"]
input.durationOptionalstringRequested output duration. Unsupported values are normalized to 5 seconds.
Available options:
"5"
input.resolutionOptionalstringRequested output resolution. Unsupported values are normalized to 1080p.
Available options:
"1080p"
input.nsfw_checkerOptionalbooleanOptional NSFW moderation switch. The adapter also accepts nsfwChecker and forwards it as nsfw_checker.
false
1curl -X POST "https://api.apipass.dev/api/v1/jobs/createTask" \
2 -H "Content-Type: application/json" \
3 -H "Authorization: Bearer YOUR_API_KEY" \
4 -d '{
5 "model": "wan/wan-2-6-video-to-video",
6 "callBackUrl": "https://your-domain.com/api/callback",
7 "input": {
8 "prompt": "The video drinks milk tea while doing some improvised dance moves to the music.",
9 "video_urls": [
10 "https://static.aiquickdraw.com/tools/example/1765957777782_cNJpvhRx.mp4"
11 ],
12 "duration": "5",
13 "resolution": "1080p",
14 "nsfw_checker": false
15 }
16 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_12345678"
6 }
7}codeStatus code. 200 indicates the task was created successfully.
messageResponse message returned by ApiPass.
data.taskIdTask identifier used for later status checks.
ByteDance
ByteDance
Starting from
0 credits
ByteDance
ByteDance
Starting from
0 credits
ByteDance
ByteDance
Turn text, images, video clips, and audio into cinematic, audio-synced videos with a single API call.
Starting from
0 credits
MiniMax
MiniMax
Starting from
0 credits
ByteDance
ByteDance
Generate cinematic 4K AI videos up to 30 seconds with Seedance 2.5's multimodal power.
Starting from
0 credits
Google Veo 3.1 is the latest state-of-the-art generative video model designed to transform text and image prompts into high-fidelity cinematic visuals. Building upon its predecessors, Veo 3.1 features significant upgrades in prompt adherence, visual realism, and native audio generation, creating 8-second clips with synchronized sound effects and dialogue.
Starting from
0 credits
wan
wan
Starting from
0 credits
Runway
Runway
Starting from
0 credits
Kling
Kling
Transform text prompts and images into high-quality videos with advanced AI. Generate cinematic content with customizable duration, aspect ratio, and audio capabilities.
Starting from
0 credits
MiniMax
MiniMax
Generate high-quality AI videos from text prompts or images with MiniMax's Hailuo 2.3 model. Support for both 6s and 10s durations, 768p and 1080p resolutions, with intelligent prompt optimization.
Starting from
0 credits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
Starting from
0 credits
Luma
Luma
Starting from
0 credits
Kling
Kling
Kling v3 video generation model, supports text-to-video and image-to-video, up to 15 seconds, 1080p pro mode
Starting from
0 credits
Starting from
0 credits
grok
grok
Starting from
0 credits
kling
kling
Starting from
0 credits