Seedance 2.5 from ByteDance is officially available on Apiframe.

AI Video Generation API

AI Video Generator API

Generate video with every leading model through one unified API. Veo 3.1, Sora 2, Kling, Seedance, Hailuo, Luma and Runway - one key, one endpoint, one bill.

POST /v2/videos/generate

Apiframe is a single AI video generator API for text-to-video and image-to-video across every major model. Switch between Veo, Sora, Kling, Seedance and more with one parameter, with synchronized audio support and pay-as-you-go pricing.

What you can build

Text-to-video

Generate cinematic clips from a prompt with Veo 3.1, Sora 2, Kling and Seedance.

Image-to-video

Animate a still image into motion with reference-image and first/last-frame support.

Native audio

Produce video with natively synchronized audio on models that support it, like Veo.

Upscaling & editing

Upscale footage with Topaz or run instruction-based video edits with Wan.

AI video models on one API

Call any of these video models with the same request shape. Pick a model to see its API reference, durations, resolutions and code samples.

Browse all AI models

How it works

  1. 1

    Get your API key

    Sign up and grab one key that works for every video model on Apiframe.

  2. 2

    POST your prompt

    Send a single request with a model id and prompt or input image. Switch models by changing one field.

  3. 3

    Poll or webhook

    Get a jobId back, then poll the job or receive a webhook with the finished video.

Example request
curl -X POST https://api.apiframe.ai/v2/videos/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "model": "...", "prompt": "..." }'

Frequently asked questions

What is the best AI video generator API?

Apiframe exposes every leading video model - Veo 3.1, Sora 2, Kling, Seedance, Hailuo, Luma and Runway - through one API, so you can compare quality, speed and cost and pick the best model per use case without integrating each provider.

Does the API support image-to-video?

Yes. Many models accept an input image plus a prompt for image-to-video, and some support first/last-frame and reference images. The capability is listed on each model page.

How much does the AI video generation API cost?

Pricing is pay-as-you-go - you only pay for successful generations. Video pricing varies by model, duration and resolution. See the pricing page for details.

Which video models are available?

Veo, Sora, Kling, Seedance, Hailuo, Luma, Runway, Wan, Midjourney Video and Grok Video - all through one API and one billing account.

Get started

Start building with the AI video generation API

One API key for every video model. Free credits to start.

  • Every top video model
  • Text & image to video
  • Webhooks, SDKs & idempotency
  • Pay only for successes