Luma AI
UNI image models and Ray video models, with generation, reference guidance and media editing.
12 native current and legacy records reviewed. Current Agents API prices and limits are separate from older Dream Machine workflows. UNI checkpoint naming, older releases and specialist identities remain under review.
Start with the job your model needs to do. Then narrow by capabilities, provider and price.
Compare every model with the same request.
Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.
12 models
| Compare | Model | Input tokensPublished limit* | Output tokensMaximum per response* | Input pricePer 1M tokens | Output pricePer 1M tokens | Cost per question1,000 input + 500 outputEstimated · uncached |
|---|---|---|---|---|---|---|
| 6,000 characterstext input | 2Koutput resolution | Usage pricing $0.0404 / imageText to image · Luma Agents API$0.0434 / imageImage reference (1 image) · Luma Agents APIRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 6,000 characterstext input | 2Koutput resolution | Usage pricing $0.10 / imageText to image · Luma Agents API$0.103 / imageImage reference (1 image) · Luma Agents APIRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| 6,000 characterstext input | 5 or 10 seconds for generation; start/end anchors and HDR require 5 secondsoutput duration | Usage pricing $0.06 / 5s video360p (draft) SDR 5s · Luma Agents API$0.18 / 10s video360p (draft) SDR 10s · Luma Agents APIRates & conditions ↗ | Different billing unitPrice details ↗ | |||
| Not collected | 5s or 9s API duration optionsoutput duration | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Not collected | 5s or 9s API duration optionsoutput duration | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Up to 4 image referencesimage references | JPEG, PNGoutput formats | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Up to 4 image referencesimage references | JPEG, PNGoutput formats | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Not collected | SDR: up to 10s text-to-video or 5s image-to-video; HDR: 5s text-to-videooutput duration | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Up to 10 secondsvideo input | 540p, 720p, 1080poutput resolution | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Up to 18 seconds for Modifyvideo input | Text-to-video 5/10s; image-to-video 5s; extensions about 30soutput duration | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Not collected | 5 secondsoutput duration | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
| Not collected | 720p, 1080poutput resolution | Usage pricingNot collected | Different billing unitPrice details ↗ | |||
* Media models show their native limits. A shared context window includes both input and output tokens.
Catalog coverage
Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.
See what is being reviewed