Which is cheaper, Ray 1.6 or Ray 3?
Ray 3 currently shows the lower $ / Video: $1.10 vs $2.40 for Ray 1.6. That is the public Luma video API pricing versus Luma video API pricing. Duration, resolution, and voice settings can still flip the invoice.
Ray 1.6 vs Ray 3
ComparisonCompare $ / Video, Text to Video, Image to Video, license, and release date. Search any video generation model with the pickers below.
Ray 1.6
Luma
$2.40
Ray 3
Luma
$1.10
Metric
Ray 1.6
Ray 3
$ / Video
$2.40
$1.10
Text to Video
-343
N/A
Image to Video
N/A
N/A
Text to Video win rate
1.7%
N/A
Release date
N/A
2025-09-19
License
Unknown
Proprietary
Provider
Luma
Luma
Ray 1.6 vs Ray 3 FAQ
Which ranks higher, Ray 1.6 or Ray 3?
Ray 1.6 currently leads on Text to Video: -343 for Ray 1.6 vs N/A for Ray 3. Rank and price move independently, so the cheaper video generation model is not automatically the weaker one.
Does this comparison include Image to Video?
Yes. Ray 1.6 scores N/A and Ray 3 scores N/A on Image to Video. If one side is N/A, that mode is missing from the public feed, not priced at zero.
Is Ray 1.6 or Ray 3 open source?
Ray 1.6 is proprietary. Ray 3 is proprietary (Proprietary). Open-weight models can be self-hosted; proprietary ones are billed only through the provider API on this page.
How do I switch the models in this Ray 1.6 vs Ray 3 comparison?
Use the model pickers at the top of this page. Search any video generation model in the index and the URL updates to a new comparison, the same way LLM comparison pages work. Open either model from the sidebar for the single-model $ / Video page.
What data is used for Ray 1.6 vs Ray 3?
This comparison uses public llm-stats and ZeroEval arena data for video generation models, then normalizes $ / Video, Text to Video, Image to Video, license, and release date inside AnotherWrapper. Treat the numbers as comparable public list rates, not a quote from either vendor.
All Video Models
Next step
You found the model. Now ship the product.
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.