From 38b9d816ebca6abd2ce0d29c28076b1432afe567 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Thu, 12 Feb 2026 01:19:07 +0000 Subject: [PATCH] docs: add reference to example_openai_endpoint repo for self-hosting fake OpenAI proxy - Updated benchmarks.md with a section on setting up fake OpenAI endpoints - Updated load_test.md to mention the self-hosted option - Updated load_test_advanced.md with a tip box about the example repo Reference: https://github.com/BerriAI/example_openai_endpoint Co-authored-by: Krish Dholakia --- docs/my-website/docs/benchmarks.md | 9 ++++++++- docs/my-website/docs/load_test.md | 5 +++-- docs/my-website/docs/load_test_advanced.md | 6 +++++- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/docs/my-website/docs/benchmarks.md b/docs/my-website/docs/benchmarks.md index a1489081b4c..1f818cef498 100644 --- a/docs/my-website/docs/benchmarks.md +++ b/docs/my-website/docs/benchmarks.md @@ -5,6 +5,13 @@ import Image from '@theme/IdealImage'; Benchmarks for LiteLLM Gateway (Proxy Server) tested against a fake OpenAI endpoint. +## Setting Up a Fake OpenAI Endpoint + +For load testing and benchmarking, you can use a fake OpenAI proxy server. LiteLLM provides: + +1. **Hosted endpoint**: Use our free hosted fake endpoint at `https://exampleopenaiendpoint-production.up.railway.app/` +2. **Self-hosted**: Set up your own fake OpenAI proxy server using [github.com/BerriAI/example_openai_endpoint](https://github.com/BerriAI/example_openai_endpoint) + Use this config for testing: ```yaml @@ -12,7 +19,7 @@ model_list: - model_name: "fake-openai-endpoint" litellm_params: model: openai/any - api_base: https://your-fake-openai-endpoint.com/chat/completions + api_base: https://exampleopenaiendpoint-production.up.railway.app/ # or your self-hosted endpoint api_key: "test" ``` diff --git a/docs/my-website/docs/load_test.md b/docs/my-website/docs/load_test.md index 4641a70366c..071b097904b 100644 --- a/docs/my-website/docs/load_test.md +++ b/docs/my-website/docs/load_test.md @@ -4,8 +4,9 @@ import Image from '@theme/IdealImage'; ## Locust Load Test LiteLLM Proxy -1. Add `fake-openai-endpoint` to your proxy config.yaml and start your litellm proxy -litellm provides a free hosted `fake-openai-endpoint` you can load test against +1. Add `fake-openai-endpoint` to your proxy config.yaml and start your litellm proxy. + +LiteLLM provides a free hosted `fake-openai-endpoint` you can load test against. You can also self-host your own fake OpenAI proxy server using [github.com/BerriAI/example_openai_endpoint](https://github.com/BerriAI/example_openai_endpoint). ```yaml model_list: diff --git a/docs/my-website/docs/load_test_advanced.md b/docs/my-website/docs/load_test_advanced.md index 3171bc33594..d35b5f74784 100644 --- a/docs/my-website/docs/load_test_advanced.md +++ b/docs/my-website/docs/load_test_advanced.md @@ -29,12 +29,16 @@ Tutorial on how to get to 1K+ RPS with LiteLLM Proxy on locust **Note:** we're currently migrating to aiohttp which has 10x higher throughput. We recommend using the `openai/` provider for load testing. +:::tip Setting Up a Fake OpenAI Endpoint +You can use our hosted fake endpoint or self-host your own using [github.com/BerriAI/example_openai_endpoint](https://github.com/BerriAI/example_openai_endpoint). +::: + ```yaml model_list: - model_name: "fake-openai-endpoint" litellm_params: model: openai/any - api_base: https://your-fake-openai-endpoint.com/chat/completions + api_base: https://exampleopenaiendpoint-production.up.railway.app/ # or your self-hosted endpoint api_key: "test" ```