diff --git a/app/api/chat/route.ts b/app/api/chat/route.ts
index c8fb0f0..55dbbde 100644
--- a/app/api/chat/route.ts
+++ b/app/api/chat/route.ts
@@ -12,7 +12,11 @@ import fs from "fs/promises"
 import { jsonrepair } from "jsonrepair"
 import path from "path"
 import { z } from "zod"
-import { getAIModel, supportsPromptCaching } from "@/lib/ai-providers"
+import {
+    getAIModel,
+    supportsImageInput,
+    supportsPromptCaching,
+} from "@/lib/ai-providers"
 import { findCachedResponse } from "@/lib/cached-responses"
 import {
     checkAndIncrementRequest,
@@ -295,6 +299,17 @@ async function handleChatRequest(req: Request): Promise<Response> {
         lastUserMessage?.parts?.filter((part: any) => part.type === "file") ||
         []
 
+    // Check if user is sending images to a model that doesn't support them
+    // AI SDK silently drops unsupported parts, so we need to catch this early
+    if (fileParts.length > 0 && !supportsImageInput(modelId)) {
+        return Response.json(
+            {
+                error: `The model "${modelId}" does not support image input. Please use a vision-capable model (e.g., GPT-4o, Claude, Gemini) or remove the image.`,
+            },
+            { status: 400 },
+        )
+    }
+
     // User input only - XML is now in a separate cached system message
     const formattedUserInput = `User input:
 """md
diff --git a/lib/ai-providers.ts b/lib/ai-providers.ts
index 2ef585b..b482143 100644
--- a/lib/ai-providers.ts
+++ b/lib/ai-providers.ts
@@ -906,3 +906,34 @@ export function supportsPromptCaching(modelId: string): boolean {
         modelId.startsWith("eu.anthropic")
     )
 }
+
+/**
+ * Check if a model supports image/vision input.
+ * Some models silently drop image parts without error (AI SDK warning only).
+ */
+export function supportsImageInput(modelId: string): boolean {
+    const lowerModelId = modelId.toLowerCase()
+
+    // Helper to check if model has vision capability indicator
+    const hasVisionIndicator =
+        lowerModelId.includes("vision") || lowerModelId.includes("vl")
+
+    // Models that DON'T support image/vision input (unless vision variant)
+    // Kimi K2 models don't support images
+    if (lowerModelId.includes("kimi") && !hasVisionIndicator) {
+        return false
+    }
+
+    // DeepSeek text models (not vision variants)
+    if (lowerModelId.includes("deepseek") && !hasVisionIndicator) {
+        return false
+    }
+
+    // Qwen text models (not vision variants like qwen-vl)
+    if (lowerModelId.includes("qwen") && !hasVisionIndicator) {
+        return false
+    }
+
+    // Default: assume model supports images
+    return true
+}