From a3fc639727a8a32b56ad46d730e2c7bb8d91d7f7 Mon Sep 17 00:00:00 2001
From: Danny Avila <danny@librechat.ai>
Date: Wed, 24 Sep 2025 07:52:58 -0400
Subject: [PATCH] feat: enhance custom params docs with Anthropic API
 compatibility with detailed parameter handling and implementation status

---
 .../object_structure/custom_params.mdx        | 41 ++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

diff --git a/pages/docs/configuration/librechat_yaml/object_structure/custom_params.mdx b/pages/docs/configuration/librechat_yaml/object_structure/custom_params.mdx
index 1434e84..f64ecb2 100644
--- a/pages/docs/configuration/librechat_yaml/object_structure/custom_params.mdx
+++ b/pages/docs/configuration/librechat_yaml/object_structure/custom_params.mdx
@@ -36,4 +36,43 @@ endpoints:
               step: 0.1
             default: 0.5
 ```
-As a result, the `Temperature` slider will be limited to the range of `0.0` and `0.7` with step of `0.1`, and a default of `0.5`. The rest of the parameters will be set to their default values.
\ No newline at end of file
+As a result, the `Temperature` slider will be limited to the range of `0.0` and `0.7` with step of `0.1`, and a default of `0.5`. The rest of the parameters will be set to their default values.
+
+### Anthropic
+
+When using `defaultParamsEndpoint: 'anthropic'`, the system provides special handling that goes beyond just displaying and using Anthropic parameter sets:
+
+<Callout type="info">
+**Anthropic API Compatibility**
+
+Setting `defaultParamsEndpoint: 'anthropic'` enables full Anthropic API compatibility for parameters, headers, and payload formatting:
+- Parameters are sent to your custom endpoint exactly as the Anthropic API expects
+- This is essential for proxy services like LiteLLM that pass non-OpenAI-spec parameters directly to the underlying provider
+- Anthropic-specific parameters like `thinking` are properly formatted
+- The `messages` payload is formatted according to Anthropic's requirements (thinking blocks and prompt caching)
+- Appropriate beta headers are automatically added based on the model as when using Anthropic directly
+</Callout>
+
+This is mainly necessary to properly format the `thinking` parameter, which is not OpenAI-compatible:
+
+```json
+{
+  "thinking": {
+    "type": "enabled",
+    "budget_tokens": 10000
+  }
+}
+```
+
+Additionally, the system automatically adds model-specific Anthropic beta headers such as:
+- `anthropic-beta: prompt-caching-2024-07-31` for prompt caching support
+- `anthropic-beta: context-1m-2025-08-07` for extended context models
+- Model-specific feature flags based on the Claude model being used
+
+This ensures full compatibility when routing through proxy services or directly to Anthropic-compatible endpoints.
+
+<Callout type="note">
+**Implementation Status**
+
+Currently, this automatic parameter and header handling is fully implemented for Anthropic endpoints. Similar behavior for other `defaultParamsEndpoint` values (e.g., `google`, `bedrock`) is planned for future updates.
+</Callout>
\ No newline at end of file