diff --git a/packages/types/src/model.ts b/packages/types/src/model.ts
index e979f654dfb..803a6d4664a 100644
--- a/packages/types/src/model.ts
+++ b/packages/types/src/model.ts
@@ -14,7 +14,11 @@ export type ReasoningEffort = z.infer<typeof reasoningEffortsSchema>
  * ReasoningEffortWithMinimal
  */
 
-export const reasoningEffortWithMinimalSchema = z.union([reasoningEffortsSchema, z.literal("minimal")])
+export const reasoningEffortWithMinimalSchema = z.union([
+	reasoningEffortsSchema,
+	z.literal("minimal"),
+	z.literal("off"),
+])
 
 export type ReasoningEffortWithMinimal = z.infer<typeof reasoningEffortWithMinimalSchema>
 
diff --git a/src/api/providers/requesty.ts b/src/api/providers/requesty.ts
index 16aefae5286..dc56e272b57 100644
--- a/src/api/providers/requesty.ts
+++ b/src/api/providers/requesty.ts
@@ -123,7 +123,9 @@ export class RequestyHandler extends BaseProvider implements SingleCompletionHan
 			model,
 			max_tokens,
 			temperature,
-			...(reasoning_effort && reasoning_effort !== "minimal" && { reasoning_effort }),
+			...(reasoning_effort &&
+				reasoning_effort !== "minimal" &&
+				reasoning_effort !== "off" && { reasoning_effort }),
 			...(thinking && { thinking }),
 			stream: true,
 			stream_options: { include_usage: true },
diff --git a/src/api/transform/reasoning.ts b/src/api/transform/reasoning.ts
index 100b1c26846..b0349deaa8c 100644
--- a/src/api/transform/reasoning.ts
+++ b/src/api/transform/reasoning.ts
@@ -34,7 +34,7 @@ export const getOpenRouterReasoning = ({
 	shouldUseReasoningBudget({ model, settings })
 		? { max_tokens: reasoningBudget }
 		: shouldUseReasoningEffort({ model, settings })
-			? reasoningEffort
+			? reasoningEffort && reasoningEffort !== "off"
 				? { effort: reasoningEffort }
 				: undefined
 			: undefined
@@ -57,7 +57,7 @@ export const getOpenAiReasoning = ({
 
 	// If model has reasoning effort capability, return object even if effort is undefined
 	// This preserves the reasoning_effort field in the API call
-	if (reasoningEffort === "minimal") {
+	if (reasoningEffort === "minimal" || reasoningEffort === "off") {
 		return undefined
 	}
 
diff --git a/src/shared/api.ts b/src/shared/api.ts
index 79001cb0ad0..6b6fb1a6dac 100644
--- a/src/shared/api.ts
+++ b/src/shared/api.ts
@@ -68,6 +68,11 @@ export const shouldUseReasoningEffort = ({
 		return false
 	}
 
+	// If reasoningEffort is explicitly set to "off", reasoning should be disabled
+	if (settings?.reasoningEffort === "off") {
+		return false
+	}
+
 	// Otherwise, use reasoning if:
 	// 1. Model supports reasoning effort AND settings provide reasoning effort, OR
 	// 2. Model itself has a reasoningEffort property
diff --git a/webview-ui/src/components/settings/ThinkingBudget.tsx b/webview-ui/src/components/settings/ThinkingBudget.tsx
index 7a85e61e7a5..2ab5fb98d36 100644
--- a/webview-ui/src/components/settings/ThinkingBudget.tsx
+++ b/webview-ui/src/components/settings/ThinkingBudget.tsx
@@ -62,8 +62,8 @@ export const ThinkingBudget = ({ apiConfiguration, setApiConfigurationField, mod
 	// Build available reasoning efforts list
 	const baseEfforts = [...reasoningEfforts] as ReasoningEffortWithMinimal[]
 	const availableReasoningEfforts: ReadonlyArray<ReasoningEffortWithMinimal> = showMinimalOption
-		? (["minimal", ...baseEfforts] as ReasoningEffortWithMinimal[])
-		: baseEfforts
+		? (["off", "minimal", ...baseEfforts] as ReasoningEffortWithMinimal[])
+		: (["off", ...baseEfforts] as ReasoningEffortWithMinimal[])
 
 	// Default reasoning effort - use model's default if available
 	// GPT-5 models have "medium" as their default in the model configuration
diff --git a/webview-ui/src/i18n/locales/en/settings.json b/webview-ui/src/i18n/locales/en/settings.json
index dfccc49cc4c..6bd6f9c2be6 100644
--- a/webview-ui/src/i18n/locales/en/settings.json
+++ b/webview-ui/src/i18n/locales/en/settings.json
@@ -465,6 +465,7 @@
 		},
 		"reasoningEffort": {
 			"label": "Model Reasoning Effort",
+			"off": "Off",
 			"minimal": "Minimal (Fastest)",
 			"low": "Low",
 			"medium": "Medium",