Dedicated model · Available as managed deployment

Request a LTX-2.5 deployment on your own DGX Spark

Lightricks' LTX-2.5 — an open-weight image-to-video model built for fast, controllable clip generation, with a Diffusers build for standard pipelines. Validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only — an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.

eu-es-1 · Málaga Available as managed deployment Image or text → video Quoted per deployment ltx-2-5.axforge.ai
Request deploymentTalk to an engineerSign in €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT Hardware rental plus a managed service quoted per deployment — both confirmed in writing before anything is billed.

Why AxForge

Why LTX-2.5 as a managed deployment

Fast image-to-videoLTX is the family known for speed: usable clips in a fraction of the time of larger video models.
Standard pipelineA Diffusers build means it drops into existing tooling — ComfyUI, custom pipelines — on your own machine.
Licence reviewedLTX-2.5 ships under Lightricks' own licence; AxForge reviews it with you and deploys under it where it applies.

Specifications

What you get

ModelLTX-2.5 — Lightricks
ModalitiesImage or text → video
Sizes19.0B
LicenceCommercial licence needed — the model's own licence; AxForge handles the licence where one is required
HardwareNVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge
Rental termHour, week, month or year
Hardware pricing€0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT
Managed serviceQuoted per deployment
RegionMálaga, Spain (eu-es-1)

Full details, benchmarks and FAQ on the LTX-2.5 page. Prices exclude VAT.

How it works

From sign-in to running

1Request deployment — describe your traffic, context needs and rental term.
2You receive the configuration, hardware rental and managed-service price in writing before anything is billed.
3AxForge deploys LTX-2.5 on a dedicated DGX Spark reserved for you.
4Point your OpenAI SDK at your own endpoint with the model name you receive.
5Adjust the term — hour, week, month or year — as your workload settles.

Request deployment or sign in to start.

FAQ

LTX-2.5 — common questions

Is LTX-2.5 on the AxForge serverless API?

Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.

What hardware does LTX-2.5 need?

A dedicated DGX Spark for the 19B Diffusers build; AxForge confirms resolution, clip length and throughput with the deployment.

Can it start from a still image?

Yes — image-to-video is what LTX-2.5 is built for; text-only prompting is also supported.

How fast is it on your hardware?

AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.

What does EU LTX-2.5 hosting cost?

Hardware by the hour, week, month or year; the managed service is quoted per deployment — both confirmed in writing before anything is billed.

Ready for LTX-2.5 on your own machine?

Request deployment Sign in Talk to an engineer

Explore

More from AxForge

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms