replicate / video
ltx-2.3-pro
High-fidelity video generation with portrait support, audio-to-video, retake, and extend. Text, image, and audio-driven creation up to 4K at 50 FPS.
lightricks/ltx-2.3-pro
Source checked: 2026-09-13 · Provider endpoint, not an independently benchmarked model.
Pricing, with its conditions.
These are source observations, not interchangeable quotes. Token, compute-time, output-duration and per-request prices cannot be compared by the number alone. Input charges and optional features may add to the total.
| Source rate | Billing unit | Conditions | Evidence |
|---|---|---|---|
| $0.08 USD | second of output video | target resolution: 1080p · or around 12 seconds for $1 | Public structured source |
| $0.16 USD | second of output video | target resolution: 2k · or around 62 seconds for $10 | Public structured source |
| $0.32 USD | second of output video | target resolution: 4k · or around 31 seconds for $10 | Public structured source |
Supported settings from the source
| fps | Frame rate in frames per second · Options: 24, 25, 48, 50 · Default: 25 |
|---|---|
| audio | Input audio file for audio_to_video task |
| duration | Duration of the video in seconds · Options: 6, 8, 10 · Default: 6 |
| resolution | Resolution quality of the generated video. Only 1080p is supported for audio_to_video, retake, and extend tasks. · Options: 1080p, 2k, 4k · Default: 1080p |
| aspect_ratio | Aspect ratio of the generated video · Options: 16:9, 9:16 · Default: 16:9 |
| generate_audio | Generate audio for the video. Used for text_to_video and image_to_video tasks. · Default: true |
| retake_duration | Duration in seconds of the section to edit. Must be at least 2 seconds. Used for retake task. · Min: 2 · Default: 2 |
| last_frame_image | Last frame image for image-to-video generation. When provided, the video interpolates between the first frame and this last frame. |
Unlisted settings, region availability, deposits, taxes and commercial terms remain unverified. Confirm the exact endpoint before purchase.