diff --git a/.changeset/breezy-bobcats-change.md b/.changeset/breezy-bobcats-change.md
new file mode 100644
index 0000000000..0a99f60a05
--- /dev/null
+++ b/.changeset/breezy-bobcats-change.md
@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Change default OpenRouter model to anthropic/claude-3.5-sonnet
diff --git a/src/shared/api.ts b/src/shared/api.ts
index 24f93e96cf..a640a1c9d7 100644
--- a/src/shared/api.ts
+++ b/src/shared/api.ts
@@ -172,7 +172,7 @@ export const bedrockModels = {
 
 // OpenRouter
 // https://openrouter.ai/models?order=newest&supported_parameters=tools
-export const openRouterDefaultModelId = "anthropic/claude-3.5-sonnet:beta" // will always exist in openRouterModels
+export const openRouterDefaultModelId = "anthropic/claude-3.5-sonnet" // will always exist in openRouterModels
 export const openRouterDefaultModelInfo: ModelInfo = {
 	maxTokens: 8192,
 	contextWindow: 200_000,
@@ -184,7 +184,7 @@ export const openRouterDefaultModelInfo: ModelInfo = {
 	cacheWritesPrice: 3.75,
 	cacheReadsPrice: 0.3,
 	description:
-		"The new Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: New Sonnet scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal\n\n_This is a faster endpoint, made available in collaboration with Anthropic, that is self-moderated: response moderation happens on the provider's side instead of OpenRouter's. For requests that pass moderation, it's identical to the [Standard](/anthropic/claude-3.5-sonnet) variant._",
+		"The new Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:\n\n- Coding: New Sonnet scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding\n- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights\n- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone\n- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)\n\n#multimodal",
 }
 
 // Vertex AI
diff --git a/webview-ui/src/components/settings/OpenRouterModelPicker.tsx b/webview-ui/src/components/settings/OpenRouterModelPicker.tsx
index 37b0bbfad3..889a636ccb 100644
--- a/webview-ui/src/components/settings/OpenRouterModelPicker.tsx
+++ b/webview-ui/src/components/settings/OpenRouterModelPicker.tsx
@@ -228,8 +228,8 @@ const OpenRouterModelPicker: React.FC<OpenRouterModelPickerProps> = ({ isPopup }
 						If you're unsure which model to choose, Cline works best with{" "}
 						<VSCodeLink
 							style={{ display: "inline", fontSize: "inherit" }}
-							onClick={() => handleModelChange("anthropic/claude-3.5-sonnet:beta")}>
-							anthropic/claude-3.5-sonnet:beta.
+							onClick={() => handleModelChange("anthropic/claude-3.5-sonnet")}>
+							anthropic/claude-3.5-sonnet.
 						</VSCodeLink>
 						You can also try searching "free" for no-cost options currently available.
 					</>