Luma Ray3.14
Ray3 line model that preceded Ray3.2. Luma's field guide describes it as the default workhorse with 5-10 second text-to-video, 5 second image-to-video, draft through 1080p native output, HDR, and start/end frame keyframes, extendable to roughly 18-30 seconds via Modify and extension.
- Up to
- 10 seconds
- Resolution
- 1080p
- Weights
- Not released
- API
- No
- Commercial use
- Permitted subject to conditions
Luma's llm-info page describes it as superseded by Ray3.2, but it remains listed on the web app pricing page.
Commercial use rights included on individual Luma plans.
- Depends on your plan tier. Commercial use rights included on individual Luma plans
Specification
- What it takes in
- text, image
- What it makes
- video
- Maximum duration
- 10 seconds
- Maximum resolution
- 1080p
- Aspect ratios
- not established
- Controls
- image-to-video, keyframes, extend
- Weights
- Not released
- API
- No
- Pricing
- web app credit-based: 80 credits per second at 1080p on Luma subscription plans; Draft mode reduces cost
- Released or updated
- not established
Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.
Strengths
- HDR output on text-to-video and image-to-video
- Draft, 540p, 720p and 1080p native resolution tiers
- Start and end frame keyframes
- Character reference capability in the Ray3 line
Weaknesses
- Superseded by Ray3.2 per Luma's own llm-info page
- Image-to-video capped at 5 seconds
- Not exposed on the current Luma Agents API, which documents only ray-3.2
- No audio generation
Best for
- web app users on existing workflows
- HDR clips at 5s
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- Luma's field guide calls Ray3.14 "the latest" and "your default workhorse for video generation", while Luma's llm-info page states Ray3.14 was superseded by Ray3.2 (released June 2026) - https://lumalabs.ai/learning-center/articles/luma-video-models-field-guide vs https://lumalabs.ai/llm-info
- Version ordering is ambiguous in Luma's own naming: Ray3.14 predates Ray3.2 according to llm-info, which is counterintuitive - https://lumalabs.ai/llm-info
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
MCP servers that front Luma AI
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
Luma
MCP server for Luma Dream Machine AI video generation.
-
Picsart GenAI
Generate and edit images, videos and audio with 150+ AI models.
-
Shortgenius
Generate AI short-form videos and auto-publish them to TikTok, YouTube, Instagram, Facebook and X.
-
Varosity
One key for AI video, voice, music, and image across 40+ frontier models. BYOK zero markup.
-
Vivideo
AI video generation via the Vivideo API: auto or manual mode, avatars, voices, brand kits.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
Luma Dream Machine / Ray2
Luma's original consumer video product (Dream Machine) and the Ray2 model family behind it, with API model IDs ray-2 and ray-flash-2 and resolution op
Video generation
Luma Ray3.2
Luma's current video model, released June 2026. Generates 5 or 10 second clips at up to 1080p from text or images, with six aspect ratios, native HDR
Video generation
Adobe Firefly Video Model
The Adobe Firefly Video Model generates video from a text prompt, optionally guided by an image used as the first or final frame. Adobe's Firefly Serv
Video generation