> ## Documentation Index
> Fetch the complete documentation index at: https://docs.higgsfield.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Video Generation API

> Generate videos from text, images, and multimodal references with Higgsfield.

<div className="models-color-scope" aria-hidden="true" />

Generate videos from text prompts, source frames, or multimodal references. Choose a featured model below, then use the workflow endpoint that matches your inputs.

## Top models

<div className="featured-model-list">
  <a className="featured-model-card" href="/docs/models/seedance-2">
    <span className="featured-model-meta"><span>ByteDance</span><span>Video</span></span>
    <span className="featured-model-title">Seedance 2.0</span>
    <span className="featured-model-description">Generate videos from text, first and last frames, or image, video, and audio references.</span>
    <span className="featured-model-link">View API reference <span>→</span></span>
  </a>

  <a className="featured-model-card" href="/docs/models/seedance-2-5">
    <span className="featured-model-meta"><span>ByteDance</span><span>Video</span></span>
    <span className="featured-model-title">Seedance 2.5</span>
    <span className="featured-model-description">Create videos from text, images, or multimodal references, then edit or extend existing footage.</span>
    <span className="featured-model-link">View API reference <span>→</span></span>
  </a>

  <a className="featured-model-card" href="/docs/models/kling-3">
    <span className="featured-model-meta"><span>Kling</span><span>Video</span></span>
    <span className="featured-model-title">Kling 3.0</span>
    <span className="featured-model-description">Cinematic text-to-video and image-to-video with fluid motion, native audio, and multiple quality tiers.</span>
    <span className="featured-model-link">View API reference <span>→</span></span>
  </a>

  <a className="featured-model-card" href="/docs/models/wan-3">
    <span className="featured-model-meta"><span>Alibaba</span><span>Video</span></span>
    <span className="featured-model-title">Wan 3.0</span>
    <span className="featured-model-description">Generate up to 30 seconds from text, first and last frames, or multimodal image, video, audio, document, and web references.</span>
    <span className="featured-model-link">View API reference <span>→</span></span>
  </a>
</div>

Explore every available video model in the [Higgsfield video generator](https://higgsfield.ai/ai/video).

## Quick start

<Steps>
  <Step title="Choose a model">
    Open a featured model page and select the endpoint that matches your inputs.
  </Step>

  <Step title="Submit the request">
    Authenticate with `Authorization: Key <key-id>:<secret>` and send the endpoint-specific JSON body.
  </Step>

  <Step title="Retrieve the video">
    [Poll the request status](/docs/concepts/polling) or configure [webhooks](/docs/how-to/webhooks) for production workloads.
  </Step>
</Steps>


## Related topics

- [Model API Reference](/docs/models.md)
- [Image Generation API](/docs/models/image-generation.md)
- [Kling 3.0 4K Image to Video API](/docs/models/kling-3/4k-image-to-video.md)
- [Seedance 2.5 Image To Video API](/docs/models/seedance-2-5/image-to-video.md)
- [Seedance 2.5 Reference To Video API](/docs/models/seedance-2-5/reference-to-video.md)