---
title: "Update Websearch Interception Settings"
method: PATCH
path: "/update/websearch_interception_settings"
tags: ["Settings"]
---

# Update Websearch Interception Settings

`PATCH /update/websearch_interception_settings`

## Request

- Base URL: `https://api.sea-lion.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.sea-lion.ai/update/websearch_interception_settings`
- Auth: API key in header `x-litellm-api-key`

Update web search interception settings in database.

Settings will be picked up by all pods within approximately 10 seconds via background polling.

## Request body

- WebSearchInterceptionSettings: Configuration for server-side web search interception
  - `enabled` boolean: Serve web search tool calls from a configured search tool instead of passing them upstream
  - `enabled_providers` string[]: LLM providers to intercept for (e.g. 'bedrock', 'vertex_ai'). Empty intercepts Bedrock only.
  - `search_tool_name` string, nullable: Name of the configured search tool to run searches through. Empty uses the first one available.
  - `max_agentic_loops` integer, nullable: How many follow-up model calls one intercepted request may chain. Empty applies the default of 3.

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

## Changes

- **2026-10-21** `f2fb14eab3f5`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/sea-lion/apis/litellm-api/changes/update/websearch_interception_settings/patch.md)

---

[API](https://skmtc.dev/sea-lion/apis/litellm-api.md) · [All operations](https://skmtc.dev/sea-lion/apis/litellm-api/llms.txt) · [OpenAPI document](https://skmtc.dev/sea-lion/apis/litellm-api/revisions/1ba9123c189a?raw)