diff --git a/packages/@n8n/nodes-langchain/nodes/chains/ChainLLM/ChainLlm.node.ts b/packages/@n8n/nodes-langchain/nodes/chains/ChainLLM/ChainLlm.node.ts
index 5c84fa16b3..71022f84fe 100644
--- a/packages/@n8n/nodes-langchain/nodes/chains/ChainLLM/ChainLlm.node.ts
+++ b/packages/@n8n/nodes-langchain/nodes/chains/ChainLLM/ChainLlm.node.ts
@@ -1,4 +1,9 @@
-import { ApplicationError, NodeConnectionType, NodeOperationError } from 'n8n-workflow';
+import {
+	ApplicationError,
+	NodeApiError,
+	NodeConnectionType,
+	NodeOperationError,
+} from 'n8n-workflow';
 import type {
 	IBinaryData,
 	IDataObject,
@@ -30,6 +35,10 @@ import {
 	isChatInstance,
 } from '../../../utils/helpers';
 import { getTracingConfig } from '../../../utils/tracing';
+import {
+	getCustomErrorMessage as getCustomOpenAiErrorMessage,
+	isOpenAiError,
+} from '../../vendors/OpenAi/helpers/error-handling';
 
 interface MessagesTemplate {
 	type: string;
@@ -580,6 +589,18 @@ export class ChainLlm implements INodeType {
 					});
 				});
 			} catch (error) {
+				// If the error is an OpenAI's rate limit error, we want to handle it differently
+				// because OpenAI has multiple different rate limit errors
+				if (error instanceof NodeApiError && isOpenAiError(error.cause)) {
+					const openAiErrorCode: string | undefined = (error.cause as any).error?.code;
+					if (openAiErrorCode) {
+						const customMessage = getCustomOpenAiErrorMessage(openAiErrorCode);
+						if (customMessage) {
+							error.message = customMessage;
+						}
+					}
+				}
+
 				if (this.continueOnFail()) {
 					returnData.push({ json: { error: error.message }, pairedItem: { item: itemIndex } });
 					continue;
diff --git a/packages/@n8n/nodes-langchain/nodes/llms/LMChatOpenAi/LmChatOpenAi.node.ts b/packages/@n8n/nodes-langchain/nodes/llms/LMChatOpenAi/LmChatOpenAi.node.ts
index 65e3145bd9..dcf483a751 100644
--- a/packages/@n8n/nodes-langchain/nodes/llms/LMChatOpenAi/LmChatOpenAi.node.ts
+++ b/packages/@n8n/nodes-langchain/nodes/llms/LMChatOpenAi/LmChatOpenAi.node.ts
@@ -5,11 +5,15 @@ import {
 	type INodeType,
 	type INodeTypeDescription,
 	type SupplyData,
+	type JsonObject,
+	NodeApiError,
 } from 'n8n-workflow';
 
 import { ChatOpenAI, type ClientOptions } from '@langchain/openai';
 import { getConnectionHintNoticeField } from '../../../utils/sharedFields';
 import { N8nLlmTracing } from '../N8nLlmTracing';
+import { RateLimitError } from 'openai';
+import { getCustomErrorMessage } from '../../vendors/OpenAi/helpers/error-handling';
 
 export class LmChatOpenAi implements INodeType {
 	description: INodeTypeDescription = {
@@ -272,6 +276,25 @@ export class LmChatOpenAi implements INodeType {
 						response_format: { type: options.responseFormat },
 					}
 				: undefined,
+			onFailedAttempt: (error: any) => {
+				// If the error is a rate limit error, we want to handle it differently
+				// because OpenAI has multiple different rate limit errors
+				if (error instanceof RateLimitError) {
+					const errorCode = error?.code;
+					if (errorCode) {
+						const customErrorMessage = getCustomErrorMessage(errorCode);
+
+						const apiError = new NodeApiError(this.getNode(), error as unknown as JsonObject);
+						if (customErrorMessage) {
+							apiError.message = customErrorMessage;
+						}
+
+						throw apiError;
+					}
+				}
+
+				throw error;
+			},
 		});
 
 		return {
diff --git a/packages/@n8n/nodes-langchain/nodes/vendors/OpenAi/actions/router.ts b/packages/@n8n/nodes-langchain/nodes/vendors/OpenAi/actions/router.ts
index b0ce414ce8..634923a5e6 100644
--- a/packages/@n8n/nodes-langchain/nodes/vendors/OpenAi/actions/router.ts
+++ b/packages/@n8n/nodes-langchain/nodes/vendors/OpenAi/actions/router.ts
@@ -12,6 +12,7 @@ import * as image from './image';
 import * as text from './text';
 
 import type { OpenAiType } from './node.type';
+import { getCustomErrorMessage } from '../helpers/error-handling';
 
 export async function router(this: IExecuteFunctions) {
 	const returnData: INodeExecutionData[] = [];
@@ -61,6 +62,15 @@ export async function router(this: IExecuteFunctions) {
 			}
 
 			if (error instanceof NodeApiError) {
+				// If the error is a rate limit error, we want to handle it differently
+				const errorCode: string | undefined = (error.cause as any).error?.error?.code;
+				if (errorCode) {
+					const customErrorMessage = getCustomErrorMessage(errorCode);
+					if (customErrorMessage) {
+						error.message = customErrorMessage;
+					}
+				}
+
 				error.context = {
 					itemIndex: i,
 				};
diff --git a/packages/@n8n/nodes-langchain/nodes/vendors/OpenAi/helpers/error-handling.ts b/packages/@n8n/nodes-langchain/nodes/vendors/OpenAi/helpers/error-handling.ts
new file mode 100644
index 0000000000..8db54a1b86
--- /dev/null
+++ b/packages/@n8n/nodes-langchain/nodes/vendors/OpenAi/helpers/error-handling.ts
@@ -0,0 +1,14 @@
+import { OpenAIError } from 'openai/error';
+
+const errorMap: Record<string, string> = {
+	insufficient_quota: 'OpenAI: Insufficient quota',
+	rate_limit_exceeded: 'OpenAI: Rate limit reached',
+};
+
+export function getCustomErrorMessage(errorCode: string): string | undefined {
+	return errorMap[errorCode];
+}
+
+export function isOpenAiError(error: any): error is OpenAIError {
+	return error instanceof OpenAIError;
+}