Run open-source video models
at a fraction of the cost
Production-ready serverless APIs for open-source video models. Lower GPU costs, no infrastructure to manage.
Everything you need to run video generation in production
Instant job queuing
Submit a generation job via API in milliseconds — queued and processed on our GPU fleet.
Lower GPU costs
Optimized inference cuts cost per second without sacrificing output quality.
Simple job API
POST a prompt, poll for status, get back a video URL. No infrastructure to manage.
Swap models, not code
Same request shape across models — change the model field, not your integration.
Built-in moderation
Every generation job passes through automatic content moderation.
Agent-native API
Designed for programmatic use, with the same API-key auth as the rest of TokenFactory.
Open-source video models, self-hosted
We run open-weight generative models on our own GPU fleet — no black-box vendor API in the loop.
MiniMax-H3
LiveOpen-weight video+audio generation, served via SGLang across our GPU fleet. Compare outputs in the Video Arena.
$0.06/sec at 768p · $0.08/sec at 2KLTX-2.3 / 2.5
Coming soonLightricks' open-weight video model. LTX-2.3 is confirmed compatible with our serving stack and is next in line to onboard.
FLUX 3
Watching for open weightsBlack Forest Labs' image/video/audio model. Currently API-only upstream — we'll self-host as soon as open weights ship.
How it works
Get an API token
Sign up and generate a scoped API token from your dashboard in seconds.
Send video generation jobs
Call the API with your prompt and model of choice to queue a video generation job.
Pull status and download
Poll the job endpoint for progress, then grab the finished video URL once it's ready.
Get early access
We're onboarding teams building with AI agents. Join the waitlist and we'll be in touch.