Wan Video
wan-videoWan Video's 8 models on ModelRunner span Image-to-Video, Video-to-Video and Text-to-Video, from $0.05 per second of video upward.
8 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Wan Video models & pricing
Wan 3.0 Image to Video
wan-video
Animate a still photo into a clip of up to 30 seconds at 480P, 720P or 1080P, optionally pinning a closing frame so the model generates the motion between two images, with a matching soundtrack included.
Wan 3.0 Text to Video
wan-video
Generate a video from a text prompt at 480P, 720P or 1080P, with a matching soundtrack included and clips running up to 30 seconds in one generation.
Wan 2.7 Video Extend
wan-video
Extend an existing video clip into a longer one - up to 15 seconds in total, with matching audio, and optionally steered toward a closing frame you supply.
Wan 2.7 Image to Video (Audio Driven)
wan-video
Drive a still photo with your own audio clip: the track is used for lip-sync and action timing, producing a 2-15 second video at 720P or 1080P that performs in time with the sound.
Wan 2.7 Image to Video
wan-video
Animate a still photo into a 2-15 second video at 720P or 1080P, optionally pinning a closing frame, with background music or sound effects generated alongside the picture.
Wan 2.2 Animate Move
wan-video
Motion control for a character image: transfer the motion and facial expressions of a driving video onto your character — no text prompt needed, just a photo and a reference clip.
Wan VACE Video Edit
wan-video
Edit an existing video from a text prompt — restyle scenes, swap subjects or backgrounds, and apply reference-image-guided changes while preserving the source motion.
Wan 2.7 Text to Video
wan-video
Generate a 2-15 second video from a text prompt at 720P or 1080P, delivered with matching background music or sound effects generated alongside the picture.
What you can build with Wan Video models
- Image to video: animate a still photo into a moving clip with sound Wan 3.0 Image to Video
- First and last frame: pin the opening and closing images and get the motion between them Wan 3.0 Image to Video
- Long video: animate a photo for up to 30 seconds in one call instead of stitching clips Wan 3.0 Image to Video
- Bring a product photo, packshot or poster to life for an ad Wan 3.0 Image to Video
- Turn an illustration or piece of concept art into a short animation Wan 3.0 Image to Video
- Text to video: turn a written scene into a finished clip with sound Wan 3.0 Text to Video
- Long video: generate up to 30 seconds in one call instead of stitching clips Wan 3.0 Text to Video
- Draft cheaply at 480P, then re-render the keeper at 1080P Wan 3.0 Text to Video
Browse by capability
Call a Wan Video model in one request
Every endpoint shares the same lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/wan-video/wan/v3.0/image-to-video \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use Wan Video models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Wan Video model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What Wan Video models can I run on ModelRunner?
The catalog has 8 public Wan Video models: Wan 3.0 Image to Video, Wan 3.0 Text to Video, Wan 2.7 Video Extend and 5 more. They cover image-to-video, video-to-video and text-to-video. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do Wan Video models cost?
Pay-per-use, with no subscription: the 8 Wan Video models billed per second of video start at $0.05, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a Wan Video model from the API?
POST to https://queue.modelrunner.run/wan-video/wan/v3.0/image-to-video with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run Wan Video models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 8 Wan Video models become tools your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.