LiteLLM
Nicholas Hopper has used LiteLLM in his work at APX Stream.
Where Nicholas Hopper has used LiteLLM
Owns inference: managed and self-hosted open-weight models behind a LiteLLM gateway with routing, fallback and cost caps, and fine-tuned models to improve answer accuracy.
Routed all model calls through a self-hosted LiteLLM gateway so services hold no provider keys, with per-key spend tracking and model aliases as the swap point between providers.