Model comparison
Compare HappyHorse 1.1 and LTX-2.3 Pro using the same provider-sourced video generation rubric. No mystery score and no invented benchmark ranking.
Facts checked September 4, 2026
Set your usage. Your estimate updates as you type.
Example: 8-second, 720p clips with audio. Models that do not support these settings will not receive an estimate.
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
| Model | Access | Estimated total (USD) |
|---|---|---|
| HappyHorse 1.1HappyHorse | HappyHorse | No reviewed rate |
| LTX-2.3 ProLightricks | Lightricks | No reviewed rate |
Quick take
Alibaba's unified video family for creating short clips with sound from text, a starting image, or a reference video.
The endpoints, accepted references, and defaults are not identical. Check watermark settings, content rules, live per-second pricing, and continuity across each shot before planning a campaign.
LTX's mature full-workflow video model for generation plus Retake, Extend, Reframe, native audio, and first-to-last-frame control.
Generation, audio-to-video, and editing endpoints do not all share one rate or limit. Pick the exact route, resolution, frame rate, and duration before comparing it with 2.5 Fast or Pro.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| Video generation | HappyHorse 1.1 | LTX-2.3 Pro |
|---|---|---|
| Generation priceCurrent list price per generated second or the provider's closest billing unit. | Per generated second; use live QwenCloud rate | $0.04/s 720p to $0.32/s 4K for text/image generation |
| Clip durationDocumented duration choices or maximum clip length. | 3–15 seconds | Up to 20 seconds depending on route and resolution |
| Maximum outputHighest provider-documented output resolution, with relevant constraints. | 1080p | 4K |
| Native audioWhether the endpoint generates synchronized audio with video. | Yes | Yes on Pro |
| Input modesSupported text, image, video, reference, or motion inputs. | Text, first image, or reference video | Text, image, audio; first/last frame; Retake, Extend, Reframe |
| Generation timeOnly shown when a provider publishes a range; not a Cody benchmark. | Not published | Not published |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
QwenCloud says API inputs and outputs are not retained for model training and are processed in memory. Confirm regional storage and any enabled conversation-storage setting for the exact account.
Provider and API links
The reviewed public LTX model and pricing guides do not state one complete endpoint-specific retention or training-use commitment. Verify current account and enterprise terms for sensitive media.
Provider and API links
Frequently asked questions
HappyHorse 1.1: Alibaba's unified video family for creating short clips with sound from text, a starting image, or a reference video. LTX-2.3 Pro: LTX's mature full-workflow video model for generation plus Retake, Extend, Reframe, native audio, and first-to-last-frame control.
Consider HappyHorse 1.1 when your priority is Short concept videos with native sound. Consider LTX-2.3 Pro when your priority is Video pipelines that need generation and editing. Test both with your own data and provider route before committing.
No. This comparison aligns provider-published facts for the Video generation category. It does not claim a universal winner or combine incompatible third-party benchmark scores.
