feat(api): add no_reasoning flag

apps/docs/content/features/routing.mdx

@@ -71,7 +71,7 @@ curl -X POST "https://api.llmgateway.io/v1/chat/completions" \
 
 ## Optimized Auto Routing
 
-Our most powerful feature is **optimized auto routing**, which automatically selects the best model for your specific use case without you having to specify a model at all.
+Auto routing automatically selects the best model for your specific use case without you having to specify a model at all.
 
 ### Current Implementation
 
@@ -120,6 +120,44 @@ curl -X POST "https://api.llmgateway.io/v1/chat/completions" \
 	the API will return an error.
 </Callout>
 
+### Reasoning models only
+
+Just specify the `reasoning_effort` value and only a model which supports reasoning will be chosen. This parameter is not specific to the auto model.
+
+```bash
+# Auto route only to reasoning models
+curl -X POST "https://api.llmgateway.io/v1/chat/completions" \
+  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "auto",
+    "messages": [{"role": "user", "content": "Hello!"}],
+    "reasoning_effort": "medium"
+  }'
+```
+
+### Exclude Reasoning Models
+
+When using auto routing, you can exclude reasoning models from selection by setting the `no_reasoning` parameter to `true`. This is useful when you want faster responses or need to avoid the additional cost and latency of reasoning models:
+
+```bash
+# Auto route excluding reasoning models
+curl -X POST "https://api.llmgateway.io/v1/chat/completions" \
+  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "auto",
+    "messages": [{"role": "user", "content": "Hello!"}],
+    "no_reasoning": true
+  }'
+```
+
+<Callout type="info">
+	The `no_reasoning` parameter only works with auto routing (`"model": "auto"`).
+	If no non-reasoning models are available that meet your request requirements,
+	the API will return an error.
+</Callout>
+
 <Callout type="success">
 	Auto routing analyzes your payload and automatically chooses between
 	cost-effective models for simple requests and more powerful models for complex

apps/gateway/src/chat/chat.ts

@@ -225,6 +225,11 @@ const completionsRequestSchema = z.object({
 			"When used with auto routing, only route to free models (models with zero input and output pricing)",
 		example: false,
 	}),
+	no_reasoning: z.boolean().optional().default(false).openapi({
+		description:
+			"When used with auto routing, exclude reasoning models from selection",
+		example: false,
+	}),
 });
 
 const completions = createRoute({
@@ -387,6 +392,7 @@ chat.openapi(completions, async (c) => {
 		tools,
 		tool_choice,
 		free_models_only,
+		no_reasoning,
 	} = validationResult.data;
 
 	// Extract reasoning_effort as mutable variable for auto-routing modification
@@ -903,6 +909,14 @@ chat.openapi(completions, async (c) => {
 				const modelContextSize = provider.contextSize ?? 8192;
 				const contextSizeMet = modelContextSize >= requiredContextSize;
 
+				// If no_reasoning is true, exclude reasoning models
+				if (
+					no_reasoning &&
+					(provider as ProviderModelMapping).reasoning === true
+				) {
+					return false;
+				}
+
 				// If reasoning_effort is specified, only include providers that support reasoning
 				if (reasoning_effort !== undefined) {
 					return (
@@ -965,6 +979,12 @@ chat.openapi(completions, async (c) => {
 					message:
 						"No free models are available for auto routing. Remove free_models_only parameter or use a specific model.",
 				});
+			} else if (no_reasoning) {
+				// If no non-reasoning models are available, return error
+				throw new HTTPException(400, {
+					message:
+						"No non-reasoning models are available for auto routing. Remove no_reasoning parameter or use a specific model.",
+				});
 			}
 		} else {
 			if (free_models_only) {
@@ -973,6 +993,12 @@ chat.openapi(completions, async (c) => {
 					message:
 						"No free models are available for auto routing. Remove free_models_only parameter or use a specific model.",
 				});
+			} else if (no_reasoning) {
+				// If no_reasoning is true but no suitable model found, return error
+				throw new HTTPException(400, {
+					message:
+						"No non-reasoning models are available for auto routing. Remove no_reasoning parameter or use a specific model.",
+				});
 			}
 			// Default fallback if no suitable model is found - use cheapest allowed model
 			usedModel = "gpt-5-nano";