diff --git a/main.py b/main.py
index 08cd174de..cda988880 100644
--- a/main.py
+++ b/main.py
@@ -21,6 +21,7 @@
 parser.add_argument("--wait-for-peers", type=int, default=0, help="Number of peers to wait to connect to before starting")
 parser.add_argument("--chatgpt-api-port", type=int, default=8000, help="ChatGPT API port")
 parser.add_argument("--chatgpt-api-response-timeout-secs", type=int, default=90, help="ChatGPT API response timeout in seconds")
+parser.add_argument("--max-generate-tokens", type=int, default=256, help="Max tokens to generate in each request")
 parser.add_argument("--inference-engine", type=str, default=None, help="Inference engine to use")
 parser.add_argument("--disable-tui", action=argparse.BooleanOptionalAction, help="Disable TUI")
 args = parser.parse_args()
@@ -38,7 +39,7 @@
     if DEBUG >= 1: print(f"Using available port: {args.node_port}")
 
 discovery = GRPCDiscovery(args.node_id, args.node_port, args.listen_port, args.broadcast_port)
-node = StandardNode(args.node_id, None, inference_engine, discovery, partitioning_strategy=RingMemoryWeightedPartitioningStrategy(), chatgpt_api_endpoint=f"http://localhost:{args.chatgpt_api_port}/v1/chat/completions", web_chat_url=f"http://localhost:{args.chatgpt_api_port}", disable_tui=args.disable_tui)
+node = StandardNode(args.node_id, None, inference_engine, discovery, partitioning_strategy=RingMemoryWeightedPartitioningStrategy(), chatgpt_api_endpoint=f"http://localhost:{args.chatgpt_api_port}/v1/chat/completions", web_chat_url=f"http://localhost:{args.chatgpt_api_port}", disable_tui=args.disable_tui, max_generate_tokens=args.max_generate_tokens)
 server = GRPCServer(node, args.node_host, args.node_port)
 node.server = server
 api = ChatGPTAPI(node, inference_engine.__class__.__name__, response_timeout_secs=args.chatgpt_api_response_timeout_secs)