Luma Ray2
Released
2025-03-15
Last refreshed
2026-10-08
Status
Researched 46d ago
ProprietaryCommercial use: restrictedMultimodalVision
Luma AI releases · 2 in the last 12 months · this family litChangelog →
Specifications
- Family
- Luma Ray
- Released
- 2025-03-15
- Specialization
- video
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
Created by
Pricing
No tracked provider pricing is available yet.
Providers(1)
About
High-fidelity video generation from images and text with physics awareness. Supports up to 4 images plus 300 character text input, 30 second extensions, and 4K upscaling.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Luma API | - | - | ServerlessPartial |
Capabilities
Multimodal
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(2)
Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 1,066 | text_to_video overall 2026-11-09Observed 2026-11-10 | Configuration: Luma Ray2 Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena text to video leaderboard, overall category, published 2026-11-09 (HF lmarena-ai/leaderboard-dataset @a31507ef, latest split; dataset main tip ec013bce). Board entry 'Luma Ray2': rank 48 of 50, Arena Score 1065.7 (95% CI 1048.3-1083.2), 5,250 votes. Organization luma-ai. Source: LMArena (CC BY 4.0). Retrieved 2026-11-10. | Source Source: LMArena (lmarena.ai), CC BY 4.0 | |
| 1,108 | image_to_video overall 2026-09-22Observed 2026-09-22 | Configuration: Overall leaderboard entry (unqualified board entry) Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: Arena score 1108 (95% CI 1092-1125), 9,521 votes, rank 46 of 48, category overall, leaderboard published 2026-09-22. Board entry 'ray2'. Source: LMArena (CC BY 4.0). Retrieved 2026-10-17. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.