Luma's latest video model, described in the sponsor segment as strong on motion, physics and 3D space.
Luma AI's Ray 3.2 video generation model with frame-level control and cross-cut continuity, via app and API.
Updated EU status checked Last shown
Ray 3.2 at a glance
- What is Ray 3.2?
- Ray 3.2 is a model from Luma AI. Luma AI's Ray 3.2 video generation model with frame-level control and cross-cut continuity, via app and API.
- Who makes Ray 3.2?
- Ray 3.2 is made by Luma AI.
- Does Ray 3.2 work in the EU?
- Unverified. The terms say the services are intended for visitors in the US and make no representation of availability elsewhere. The privacy policy covers EEA users, with legal bases and rights, but says data is processed in the US. There is no explicit EU block or supported-countries list. Last verified 14 Nov 2026.
- How much does Ray 3.2 cost?
- Freemium. Site says "Try it free". Individual plans listed at $30/month, $90/month and $300/month (about 20% less billed yearly), plus business plans. Per-generation costs are listed for video, image and audio. A separate API exists. Licence: Proprietary.
- Where was Ray 3.2 shown?
- In 1 creator video by AI Search. Most recently by AI Search on 22 Sept 2026, at 11:15 in “Finally! New best local AI image editor is here”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Ray 3.2 is a video generation model from Luma AI, listed on Luma's site as the current release in its Ray family. Luma describes it as giving control over every frame, holding continuity across cuts, and producing output in cinematic quality. Creators who mentioned it described Luma's latest video model as strong on motion, physics and 3D space.
It is available through the Luma platform, where creative agents work across video, image, audio and text, and through a Ray 3.2 API announced by Luma. Luma sells subscription plans (individual and business) and lists per-generation costs for video, image and audio.
Luma's terms of service and privacy policy state that the services are hosted in the United States and intended for visitors located in the US. Detailed technical specifications such as resolution, clip length and benchmarks were not included in the material provided.
- Frame-level control over generated video
- Continuity maintained across cuts
- Cinematic-quality output
- Available in the Luma app and via API
- Part of Luma's platform alongside the Uni image model and creative agents
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Similar AI tools
Closest neighbours by meaning, not just by category.
Luma Agents
App · Luma AI
Creative AI platform from Luma AI with agents that plan and generate video, image, audio and text assets using Ray and Uni models.
MAI Image 2.5
Model · Microsoft
Microsoft AI's text-to-image and image-editing model, with a lower-cost Flash variant, offered via Microsoft Foundry.
Veo 3.1
Model · Google
Google DeepMind's video generation model producing clips with natively generated audio, dialogue and sound effects.
MAI-Image-2.5-Pro
Model · Microsoft
Microsoft AI's text-to-image and image-editing model in the MAI Image family, with accurate text rendering.
Wan3.0
Model · Alibaba
Alibaba's Wan video generation model, reported to produce clips up to about 30 seconds, available via the Wan platform.
LTX 2.5
Model · Lightricks
Open-weights Lightricks video model with native audio, multi-shot generation, auto duration and up to 4K output.
