diff --git a/src/vs/workbench/contrib/void/browser/react/src/sidebar-tsx/SidebarChat.tsx b/src/vs/workbench/contrib/void/browser/react/src/sidebar-tsx/SidebarChat.tsx
index 96e22bd4..979ae67b 100644
--- a/src/vs/workbench/contrib/void/browser/react/src/sidebar-tsx/SidebarChat.tsx
+++ b/src/vs/workbench/contrib/void/browser/react/src/sidebar-tsx/SidebarChat.tsx
@@ -1020,7 +1020,7 @@ export const SidebarChat = () => {
 
 		{/* error message */}
 		{latestError === undefined ? null :
-			<div className='px-2'>
+			<div className='px-2 my-1'>
 				<ErrorDisplay
 					message={latestError.message}
 					fullError={latestError.fullError}
diff --git a/src/vs/workbench/contrib/void/electron-main/llmMessage/MODELS.ts b/src/vs/workbench/contrib/void/electron-main/llmMessage/MODELS.ts
index 6d39ee9f..872d5058 100644
--- a/src/vs/workbench/contrib/void/electron-main/llmMessage/MODELS.ts
+++ b/src/vs/workbench/contrib/void/electron-main/llmMessage/MODELS.ts
@@ -10,7 +10,7 @@ import { Ollama } from 'ollama';
 import { Model as OpenAIModel } from 'openai/resources/models.js';
 import { OllamaModelResponse, OnText, OnFinalMessage, OnError, LLMChatMessage, LLMFIMMessage, ModelListParams } from '../../common/llmMessageTypes.js';
 import { InternalToolInfo, isAToolName } from '../../common/toolsService.js';
-import { defaultProviderSettings, ProviderName, SettingsOfProvider } from '../../common/voidSettingsTypes.js';
+import { defaultProviderSettings, displayInfoOfProviderName, ProviderName, SettingsOfProvider } from '../../common/voidSettingsTypes.js';
 import { prepareFIMMessage, prepareMessages } from './preprocessLLMMessages.js';
 import { extractReasoningFromText } from '../../browser/helpers/extractCodeFromResult.js';
 
@@ -79,6 +79,8 @@ const modelOptionDefaults: ModelOptions = {
 	supportsReasoningOutput: false,
 }
 
+const invalidApiKeyMessage = (providerName: ProviderName) => `Invalid ${displayInfoOfProviderName(providerName).title} API key.`
+
 
 // ---------------- OPENAI ----------------
 const openAIModelOptions = { // https://platform.openai.com/docs/pricing
@@ -644,7 +646,7 @@ const _sendOpenAICompatibleFIM = ({ messages: messages_, onFinalMessage, onError
 			onFinalMessage({ fullText, });
 		})
 		.catch(error => {
-			if (error instanceof OpenAI.APIError && error.status === 401) { onError({ message: 'Invalid API key.', fullError: error }); }
+			if (error instanceof OpenAI.APIError && error.status === 401) { onError({ message: invalidApiKeyMessage(providerName), fullError: error }); }
 			else { onError({ message: error + '', fullError: error }); }
 		})
 }
@@ -710,7 +712,7 @@ const _sendOpenAICompatibleChat = ({ messages: messages_, onText, onFinalMessage
 		})
 		// when error/fail - this catches errors of both .create() and .then(for await)
 		.catch(error => {
-			if (error instanceof OpenAI.APIError && error.status === 401) { onError({ message: 'Invalid API key.', fullError: error }); }
+			if (error instanceof OpenAI.APIError && error.status === 401) { onError({ message: invalidApiKeyMessage(providerName), fullError: error }); }
 			else { onError({ message: error + '', fullError: error }); }
 		})
 }
@@ -803,7 +805,7 @@ const sendAnthropicChat = ({ messages: messages_, onText, providerName, onFinalM
 	})
 	// on error
 	stream.on('error', (error) => {
-		if (error instanceof Anthropic.APIError && error.status === 401) { onError({ message: 'Invalid API key.', fullError: error }) }
+		if (error instanceof Anthropic.APIError && error.status === 401) { onError({ message: invalidApiKeyMessage(providerName), fullError: error }) }
 		else { onError({ message: error + '', fullError: error }) }
 	})
 	_setAborter(() => stream.controller.abort())
diff --git a/src/vs/workbench/contrib/void/electron-main/llmMessage/preprocessLLMMessages.ts b/src/vs/workbench/contrib/void/electron-main/llmMessage/preprocessLLMMessages.ts
index 1aec2649..40eb880c 100644
--- a/src/vs/workbench/contrib/void/electron-main/llmMessage/preprocessLLMMessages.ts
+++ b/src/vs/workbench/contrib/void/electron-main/llmMessage/preprocessLLMMessages.ts
@@ -335,9 +335,9 @@ export const prepareFIMMessage = ({
 }) => {
 
 	let prefix = `\
-## You are a helpful coding assistant that performs autocomplete (fill-in-the middle or "FIM") for the user.
+## You are a helpful coding assistant that performs autocomplete.
 ${!aiInstructions ? '' : `\
-## Special user instructions:
+## Instructions:
 ${aiInstructions.split('\n').map(line => `##${line}`).join('\n')}`}
 
 ${messages.prefix}`