---
title: "LiteLLM Proxy Performance"
url: "/docs/proxy/perf"
canonical_url: "https://docs.litellm.ai/docs/proxy/perf"
type: "docs"
last_updated: "2026-10-06"
summary: "The numbers on this page compare the proxy against calling a provider directly. For gateway capacity numbers (requests, tokens, and latency per pod at scale) see Benchmarks."
---
# LiteLLM Proxy Performance

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt


The numbers on this page compare the proxy against calling a provider directly. For gateway capacity numbers (requests, tokens, and latency per pod at scale) see [Benchmarks](../benchmarks.md).

### Throughput - 30% Increase
LiteLLM proxy + Load Balancer gives **30% increase** in throughput compared to Raw OpenAI API

### Latency Added - 0.00325 seconds
LiteLLM proxy adds **0.00325 seconds** latency as compared to using the Raw OpenAI API