seedanceapi
Ray 3.2 · Video Edit render example

Luma AI · Ray 3.2 · video to video

Ray 3.2 · Video Edit

Render Ray 3.2 through the same job workflow as Seedance — from $0.972 per render.

Model idluma/ray-3.2/video-editShot spec540p · 720p · 1080p · 5sRatefrom $0.972

What it renders

Luma Ray 3.2 Video Edit is a fast AI video-to-video editing model that re-renders an existing source video from a text prompt while preserving the original motion and timing. Hand over the model id and your shot settings, keep the job id, and collect the finished clip once the job lands. Pricing is per completed render from $0.972 and is locked in before the first frame is queued.

  1. Motion-first defaults

    Ray 3.2 · Video Edit opens on workable shot framing before you tune anything.

  2. Async by design

    Renders run as background jobs; poll at your own pace instead of holding a connection open.

  3. Clip-ready output

    Results arrive as a downloadable asset from private storage with a short-lived link.

  4. Video to Video shots

    Video to Video stays available for Ray 3.2 · Video Edit without leaving the video workspace.

  5. Ray 3.2 shots

    Ray 3.2 stays available for Ray 3.2 · Video Edit without leaving the video workspace.

  6. Video shots

    Video stays available for Ray 3.2 · Video Edit without leaving the video workspace.

From the shot board

Ray 3.2 · Video Edit example output.
Ray 3.2 · Video Edit output

Wire the render pipeline

  1. Grab a key

    Sign in, create a server-side key and add a little balance.

  2. Confirm the endpoint

    GET /v1/models lists luma/ray-3.2/video-edit with its shot limits and current rate.

  3. Queue the render

    POST /v1/jobs with the model id, your shot settings and a unique Idempotency-Key.

  4. Collect the clip

    Poll GET /v1/jobs/{id} until it lands, then fetch GET /v1/jobs/{id}/content.

Queue the render

# Seedance API — queue one render
curl https://seedanceapi.pro/v1/jobs \
  -H "Authorization: Bearer $SEEDANCE_API_KEY" \
  -H "Idempotency-Key: $REQUEST_ID" \
  -H "Content-Type: application/json" \
  -d '{"model":"luma/ray-3.2/video-edit","duration":5,"prompt":"A slow dolly across a rain-lit neon street, shallow depth of field.","resolution":"540p"}'

Shot settings

durationoptional
integer · 5 / 10
promptoptional
string
resolutionoptional
string · 540p / 720p / 1080p
start_imageoptional
string
videoneeded
string

Try a render from here

This queues a real job on this site's /v1/jobs using your signed-in balance, or an API key if you are not signed in. A pasted key lives only in this tab; the render is billed at the quoted USD rate.

Or sign in to use your account balance.

Before you wire it in

How do I start a Ray 3.2 · Video Edit render?

Authenticate, check the live model list for luma/ray-3.2/video-edit, then POST the model id and shot settings to /v1/jobs with an Idempotency-Key. Poll the job id until it settles, then download the clip.

What can I control on Ray 3.2 · Video Edit?

Ray 3.2 · Video Edit accepts duration, prompt, resolution, start_image, video. Unknown keys are rejected before the render is queued, so a typo never burns a job.

What does a Ray 3.2 · Video Edit render cost?

Pricing is per render and starts at $0.972. The exact figure for your settings is returned by the model list and reserved before the job is accepted.

Is the same Seedance key valid for Ray 3.2 · Video Edit?

Yes — Ray 3.2 · Video Edit runs on the same account, key and wallet as Seedance. Each endpoint is enabled individually, so verify the route before you depend on it.

Why does my Ray 3.2 · Video Edit job show as queued?

Video rendering is asynchronous: queued and running are normal. Keep polling until the job succeeds, fails or asks for review, and never resubmit the same Idempotency-Key expecting a second render.

More endpoints like this