Ray2 from Luma AI represents the next generation of video models, capable of creating realistic visuals with natural, coherent motion. High quality, consistency and prompt adherence make it perfectly suited for the full spectrum of professional creative work.
Ray2 has been built at significant scale, with 10x the compute and data as the previous version. This scale has provided the model new capabilities to generate video sequences with natural motion that maintain visual coherence and logical continuity throughout their duration. It represents a new frontier of video models, bringing generative AI into the realm of production-ready content.
Luma's models are built for professionals in creative work. The model's aesthetics has been tuned in collaboration with designers and artists, and trained on real-life professional-standard content to ensure it can match professionals' intentions. Luma is also deeply focused on intuitive user experience, and so Ray2 only needs natural language text, removing technical prompt engineering as a barrier for good results. Ray2 sees significant application for creative professionals across media, marketing, design, and retail. It is well-suited to help iterate on ideas; convert ideas to pre-visualizations and even create production content.
Highlights
Natural motion and physics simulation brings next-level realism to the generations
Close instruction following ensures that generations match users' vision and stylistic intention
True natural language prompting removes need for technical prompt engineering
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
This listing bills by usage, so you pay for each second of video you generate. There are no upfront commitments or subscription tiers. The two pricing dimensions differ only by output resolution. One covers video generated at 720p, 24 frames per second. The other covers video generated at 540p, 24 frames per second. Both use the same unit: one second of generated video. Your total cost scales with how many seconds you produce and which resolution you choose. Higher resolution output carries a different per-second rate than lower resolution output.
Top-of-mind questions for buyers
What counts as one billable unit for this product?
One unit is one second of generated video at a set resolution and 24 frames per second. You pick either 720p or 540p output. Each second you generate is metered, so a five-second clip counts as five units at your chosen resolution.
Do I pay a subscription or commit upfront to use this product?
No. Billing is usage-based with no upfront commitment. You pay per second of video you generate. Charges accrue only when you produce output. If you generate nothing in a period, no video charges apply for that period.
How does my cost change if I generate longer videos or switch resolution?
Cost scales directly with the number of seconds you generate. A ten-second clip costs twice a five-second clip at the same resolution. Switching between 720p and 540p changes the per-second rate. Total cost equals seconds produced multiplied by the rate for your chosen resolution.
lumalabs.ai
Helpful?
Vendor refund policy
We do not currently offer refunds
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
For any questions please reach out to AWS Support -
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
OpenAI GPT-5.5 brings OpenAIs most capable model for complex professional work to coding, analysis, software operation,and long-running agentic tasks through OpenAI APIs and Amazon Bedrock.
OpenAI GPT-5.6 Sol brings OpenAI flagship GPT-5.6 model for advanced reasoning, coding, scientific research, cybersecurity, and agentic workflows to Amazon Bedrock.
OpenAI GPT-5.6 Terra brings a balanced GPT-5.6 model for everyday work, software engineering, knowledge workflows, and scalable AI applications to Amazon Bedrock.
In the hands of a knowledgeable operator, Luma's Ray2 is one of the best currently available foundation models for video generation, with commensurate on-demand pricing through AWS Bedrock. The model is particularly good at photo-realistic rendering of human characters. We would use this much more, if it were more economical.
User
Hugely overpriced & mediocre video output, beware!
Reviewed on Feb 12, 2025
Review from a verified AWS customer
Massively overpriced compared to other models on the market, with a mediocre video output. Switching to another model for my future work.