Lightricks LTX
Explore Lightricks LTX models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Lightricks LTXltx
No provider claimThese privacy labels describe Lightricks LTX, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | Lightricks LTX |
|---|---|
| Routing status | Active |
| Provider website | https://ltx.io/ |
| Models | 2 public models |
| Credits routes | 2 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | No provider-ZDR, confidential-compute, or E2EE claim is tracked for the LTX video API. TrustedRouter relays and does not durably store prompt or generated video content. Policy source |
Models served by Lightricks LTX.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
lightricks/ltx-2.3Lightricks LTX 2.3 |
— | 5,000 | selected route | Not published | selected route |
lightricks/ltx-2.3-fastLightricks LTX 2.3 Fast |
— | 5,000 | selected route | Not published | selected route |
Questions
Does Lightricks LTX have zero data retention?
TrustedRouter does not currently mark Lightricks LTX as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Lightricks LTX end-to-end encrypted?
TrustedRouter does not currently mark Lightricks LTX as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Lightricks LTX models are available through TrustedRouter?
This page currently lists 2 public Lightricks LTX models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.