diff --git a/modal/serve.py b/modal/serve.py
index fc0df394..7589798a 100644
--- a/modal/serve.py
+++ b/modal/serve.py
@@ -229,7 +229,7 @@ class Inference:
 
         messages = request.get("messages", [])
         temperature = min(max(request.get("temperature", 0.8), 0.0), 2.0)
-        max_tokens = min(max(request.get("max_tokens", 512), 1), 2048)
+        max_tokens = min(max(request.get("max_tokens", 1024), 1), 4096)
         top_k = min(max(request.get("top_k", 50), 0), 200)
         force_web_search = bool(request.get("force_web_search", False))
 
diff --git a/services/chat-api/src/config.py b/services/chat-api/src/config.py
index bc3ae51a..36b05e98 100644
--- a/services/chat-api/src/config.py
+++ b/services/chat-api/src/config.py
@@ -23,7 +23,7 @@ class Settings(BaseSettings):
     auth_cache_max_size: int = Field(default=1024)
 
     inference_default_temperature: float = Field(default=0.8)
-    inference_default_max_tokens: int = Field(default=512)
+    inference_default_max_tokens: int = Field(default=1024)
     inference_default_top_k: int = Field(default=50)
 
     frontend_url: str = Field(default="http://localhost:3000")