Teams running LiteLLM in production.
What engineering teams at NVIDIA, Netflix, Okta, Lemonade and AT&T say about running LiteLLM.
01
Customer stories
How teams rolled out LiteLLM, with the numbers they shared.
01
In their words
Pick a company to read what its engineers said.
Single access source with consistency
“LiteLLM gives NVIDIA engineers a single, consistent way to access more than 100 AI model endpoints across cloud providers, open source deployments, and internal NVIDIA services.”
New models in a day, not hours of rework
“LiteLLM has let my team provide the latest LLM models to our users usually within a day of them being released. Without LiteLLM this would be hours of work each time — it has saved us months of work.”
David LeenStaff Software Engineer, NetflixSwap models without new security reviews
“If we decide to switch the backend model, it’s a simple configuration update in the gateway; no code changes, procurement cycles, or repetitive security reviews required.”
Dennis HenryProductivity Architect, OktaMultiple models, one interface
“LiteLLM streamlines the complexities of managing multiple LLM models.”
Mark KoltnukPrincipal Architect, GenAI Platform, LemonadeCutting AI costs
“After the company began using router provider LiteLLM, the costs of some advanced AI tasks such as coding fell by as much as 56%”
Also running LiteLLM
Written about in public
