Skip to content

Luma · Video

Ray 3.2 API pricing

luma/ray-3.2

Video generation with keyframes and HDR. Ray 3.2 by Luma, routed through INFRO on a Luma account you connect — alongside every other provider you run. Luma bills you for it directly, on that account and at your own rate. INFRO adds routing, failover, request logs, cost attribution and policy around it, and takes no part of what you pay Luma.

Pricing

Per secondUSD · updated 2026-10-05

Luma rate

$0.06

per second, billed to you by Luma

INFRO adds

$0

0% markup on model spend

Calling Ray 3.2

POST /v1/videos
import os
from infro import Infro

client = Infro(api_key=os.environ["INFRO_API_KEY"])

# Video runs as an async job — you get an id back immediately.
job = client.videos.create(
    model="luma/ray-3.2",
    prompt="drone shot over a coastline at sunrise",
    duration_seconds=6,
    webhook={"url": "https://api.acme.com/hooks/infro"},
)

What this modality supports

  • Async jobs
  • Signed webhooks
  • Lip sync & avatars
  • Permanent output URLs

Text-to-video, image-to-video, lip sync, and talking avatars as managed async jobs. Submit, get a job id, receive a signed webhook when the render lands. Finished media is re-hosted on our CDN under your account, so output links don't expire underneath you.

Same modality, nearest in price. All of them share the request shape above, so comparing them is a one-word change.

Work out what Ray 3.2 would cost you

Put your current spend on this model into the calculator and see the same workload priced here — or have us read your real usage.