From f2992047705bbef4840abe40657254c5569e73c0 Mon Sep 17 00:00:00 2001 From: Tim Pietrusky Date: Thu, 23 Apr 2026 10:54:24 +0200 Subject: [PATCH] docs: fix anthropic messages path and missing comma in routes list --- .runpod/README.md | 2 +- README.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.runpod/README.md b/.runpod/README.md index 303ab47..6eb8652 100644 --- a/.runpod/README.md +++ b/.runpod/README.md @@ -175,7 +175,7 @@ Supports the [OpenAI Responses API](https://platform.openai.com/docs/api-referen #### Anthropic Messages API -**Path:** `/anthropic/v1/messages` +**Path:** `/openai/v1/messages` Supports the [Anthropic Messages API](https://docs.anthropic.com/en/api/messages) format. Served directly, bypassing the RunPod queue. diff --git a/README.md b/README.md index 877a0f1..0c7f0e5 100644 --- a/README.md +++ b/README.md @@ -154,7 +154,7 @@ You can deploy **any model on Hugging Face** that is supported by vLLM. For the # Usage: OpenAI Compatibility -The vLLM Worker is fully compatible with OpenAI's API, and you can use it with any OpenAI Codebase by changing only 3 lines in total. The supported routes are Chat Completions, Models Responses, and Messages - with both streaming and non-streaming. +The vLLM Worker is fully compatible with OpenAI's API, and you can use it with any OpenAI Codebase by changing only 3 lines in total. The supported routes are Chat Completions, Models, Responses, and Messages - with both streaming and non-streaming. ## Modifying your OpenAI Codebase to use your deployed vLLM Worker