Private beta · OpenAI-compatible · Shared GPU fleet
Deploy fine-tuned LoRA adapters in one command
Push your adapter with the CLI and get a live, OpenAI-compatible endpoint on a shared fleet of open models. No GPUs to rent, no servers to babysit.
No credit card required. Free during the beta
▁▂▄▇ lorivo.dev CLI 0.2.0
✓ Validated my-lora - rank 32, 2 file(s), 96.4 MiB
✓ Uploaded v1 in 3.2s [3.2s]
✓ Deployed my-lora v1 (LOADED)
Live at: https://lorivo.dev/v1/responses
Model: qwen3-4b:my-lora
Try it:
curl https://lorivo.dev/v1/responses \
-H "Authorization: Bearer ad_…" \
-H "Content-Type: application/json" \
-d '{"model":"qwen3-4b:my-lora","input":"Hello!"}'$ curl -fsSL https://lorivo.dev/install.sh | sh
Your model, live in seconds
The CLI validates, uploads, and deploys your adapter, then hands you a URL that works with any OpenAI client.
curl https://lorivo.dev/v1/responses \-H "Authorization: Bearer ad_…" \-H "Content-Type: application/json" \-d '{"model":"qwen3-4b:my-lora","input":"Hello!"}'
Built for developers
OpenAI-compatible endpoint
Point your existing chat code at /v1/chat/completions or /v1/responses and swap models by changing one string.
Instant rollbacks
Every version is kept. Promote, roll back, and A/B test the base model against your adapter in the playground.
Org-scoped API keys
Keys are scoped to your organization, shown once at creation, and revocable from the dashboard.
Everything in one dashboard
How it works
Create an account
Free beta account. You get one organization and dashboard access.
Grab an API key
One click on the dashboard, scoped to your org.
Log in with your key
Run lorivo login <api-key>. The CLI stores your key locally.
Deploy your adapter
Run lorivo deploy ./my-lora and get a live URL back in seconds.
Ready to ship your first adapter?
Free during the beta. Bring a trained LoRA and deploy it in minutes.
Join the beta