LTX logo

LTX

Free tier

Open Foundation Models for Video, Audio, and World Simulation

Free tier available·All audiences·Powered by LTX (proprietary models: LTX-2.5, LTX-2.3, LTX-2, LTXV; also integrates partner models: Veo 3.1, FLUX.2 Pro, Kling, Seedance, GPT Image, Nano Banana 2)·API available·Open source

Key strengths

Open-weight video and world simulation modelsSelf-hostable and fine-tunable on own hardwareFree under $10M ARR licensingReal-time video generation capabilitySupports robotics, physical AI, medical, gaming, and creative production use casesAPI access availableDiffusion Fidelity Rendering technologyLoRA training supportHDR and alpha channel video generation
Free tier + paid plans · from $15 USD/mo
Self-hostable
No ratings yet

LTX is a freemium AI platform built around open-weight video, audio, and world-simulation models. The core model family — LTX-2.5, LTX-2.3, LTX-2, and LTXV — is open-source, self-hostable, and fine-tunable on your own hardware. LTX also surfaces partner models (Veo 3.1, FLUX.2 Pro, Kling, Seedance, GPT Image, Nano Banana 2) through a unified API, making it a multi-model inference layer as well as a first-party model provider.

Key technical capabilities include:

  • Real-time video generation powered by Diffusion Fidelity Rendering technology
  • HDR and alpha-channel video output for compositing pipelines
  • LoRA training support for domain-specific fine-tuning
  • API access for programmatic generation and workflow automation
  • Self-hosting — deploy on your own infrastructure with no platform dependency
  • Free commercial use for organizations under $10M ARR under the open license

Integrations span ComfyUI, HuggingFace, Fal, and ElevenLabs, enabling drop-in adoption within existing ML and creative-production stacks. Pricing starts at $0 (800 one-time credits) and scales to $125/mo for Pro (110,000 credits/mo), with Enterprise custom pricing and 20% off on annual billing.