From 27a755eb84b05df04d1e1e4d4fec155ed1ee8ff0 Mon Sep 17 00:00:00 2001 From: berri-teddy Date: Sun, 21 Sep 2025 15:08:44 -0700 Subject: [PATCH] Update docs to explainb bridging between endpoints and mode --- docs/my-website/docs/completion/usage.md | 1 + docs/my-website/docs/response_api.md | 3 +++ 2 files changed, 4 insertions(+) diff --git a/docs/my-website/docs/completion/usage.md b/docs/my-website/docs/completion/usage.md index 2a9eab941e..c388e5bfee 100644 --- a/docs/my-website/docs/completion/usage.md +++ b/docs/my-website/docs/completion/usage.md @@ -26,6 +26,7 @@ response = completion( print(response.usage) ``` +> **Note:** LiteLLM supports endpoint bridging—if a model does not natively support a requested endpoint, LiteLLM will automatically route the call to the correct supported endpoint (such as bridging `/chat/completions` to `/responses` or vice versa) based on the model's `mode`set in `model_prices_and_context_window`. ## Streaming Usage diff --git a/docs/my-website/docs/response_api.md b/docs/my-website/docs/response_api.md index 94d7c73be0..c1aa486173 100644 --- a/docs/my-website/docs/response_api.md +++ b/docs/my-website/docs/response_api.md @@ -3,8 +3,11 @@ import TabItem from '@theme/TabItem'; # /responses [Beta] + LiteLLM provides a BETA endpoint in the spec of [OpenAI's `/responses` API](https://platform.openai.com/docs/api-reference/responses) +Requests to /chat/completions may be bridged here automatically when the provider lacks support for that endpoint. The model’s default `mode` determines how bridging works.(see `model_prices_and_context_window`) + | Feature | Supported | Notes | |---------|-----------|--------| | Cost Tracking | ✅ | Works with all supported models |