Wan API
1 endpoint on fal.ai, paid per call at the provider's price.
Versions
Inputs
- Prompt
- The text prompt describing the desired video motion
- Image URL
- URL of the image to use as the first frame
- Seed
- Random seed for reproducibility. Optional
- Resolution
- Video resolution (720p or 1080p). Optional
- Enable safety checker
- If set to true, the safety checker will be enabled. Optional
- Enable prompt expansion
- Whether to enable prompt rewriting using LLM. Optional
- Audio URL
- URL of the audio to use as the background music. Optional
- Multi shots
- When true, enables intelligent multi-shot segmentation. Optional
- Duration
- Duration of the generated video in seconds. Optional
- Negative prompt
- Negative prompt to describe content to avoid. Optional
Other video generation models
- Seedance7 toolsUsage based
- Kling6 tools$0.112/s
- Veo 3.14 toolsUsage based
- Gemini Omni3 toolsUsage based
- MiniMax Hailuo20 tools$0.002/s
- LTX2 toolsUsage based
- Luma Ray2 tools$0.03/s
- PixVerse2 toolsUsage based
- Grok Imagine Video5 toolsUsage based
- Vidu2 toolsUsage based
- Talking avatar (OmniHuman)1 toolUsage based
- Lip sync5 tools$0.07/unit
Questions
Which Wan versions can my agent run?
Wan 2.6 image to video.
How is it billed?
At the cost the provider reports for each call, with no markup. Your agent sees the maximum before it runs a tool.
Connect your agent to 2,400+ tools for free
Sign in with Google or GitHub. No card required.