diff --git a/backend/core/models/brains.py b/backend/core/models/brains.py
index ab7af6d62..9ccdf6ef8 100644
--- a/backend/core/models/brains.py
+++ b/backend/core/models/brains.py
@@ -16,7 +16,7 @@ class Brain(BaseModel):
     name: Optional[str] = "Default brain"
     description: Optional[str] = "This is a description"
     status: Optional[str] = "private"
-    model: Optional[str] = "gpt-3.5-turbo-0613"
+    model: Optional[str] = "gpt-3.5-turbo"
     temperature: Optional[float] = 0.0
     max_tokens: Optional[int] = 256
     openai_api_key: Optional[str] = None
diff --git a/backend/core/models/chats.py b/backend/core/models/chats.py
index c89d2da65..e1cbb0f99 100644
--- a/backend/core/models/chats.py
+++ b/backend/core/models/chats.py
@@ -17,7 +17,7 @@ class ChatMessage(BaseModel):
 
 
 class ChatQuestion(BaseModel):
-    model: str = "gpt-3.5-turbo-0613"
+    model: str = "gpt-3.5-turbo"
     question: str
     temperature: float = 0.0
     max_tokens: int = 256
diff --git a/backend/core/models/databases/supabase/brains.py b/backend/core/models/databases/supabase/brains.py
index 4eec64a01..1320a924e 100644
--- a/backend/core/models/databases/supabase/brains.py
+++ b/backend/core/models/databases/supabase/brains.py
@@ -13,7 +13,7 @@ class CreateBrainProperties(BaseModel):
     name: Optional[str] = "Default brain"
     description: Optional[str] = "This is a description"
     status: Optional[str] = "private"
-    model: Optional[str] = "gpt-3.5-turbo-0613"
+    model: Optional[str] = "gpt-3.5-turbo"
     temperature: Optional[float] = 0.0
     max_tokens: Optional[int] = 256
     openai_api_key: Optional[str] = None
diff --git a/backend/core/routes/chat_routes.py b/backend/core/routes/chat_routes.py
index 4c0aaa93a..b6535fdee 100644
--- a/backend/core/routes/chat_routes.py
+++ b/backend/core/routes/chat_routes.py
@@ -182,7 +182,7 @@ async def create_question_handler(
         or not chat_question.max_tokens
     ):
         # TODO: create ChatConfig class (pick config from brain or user or chat) and use it here
-        chat_question.model = chat_question.model or brain.model or "gpt-3.5-turbo-0613"
+        chat_question.model = chat_question.model or brain.model or "gpt-3.5-turbo"
         chat_question.temperature = chat_question.temperature or brain.temperature or 0
         chat_question.max_tokens = chat_question.max_tokens or brain.max_tokens or 256
 
@@ -254,7 +254,7 @@ async def create_stream_question_handler(
         or not chat_question.max_tokens
     ):
         # TODO: create ChatConfig class (pick config from brain or user or chat) and use it here
-        chat_question.model = chat_question.model or brain.model or "gpt-3.5-turbo-0613"
+        chat_question.model = chat_question.model or brain.model or "gpt-3.5-turbo"
         chat_question.temperature = chat_question.temperature or brain.temperature or 0
         chat_question.max_tokens = chat_question.max_tokens or brain.max_tokens or 256
 
diff --git a/backend/core/tests/test_brains.py b/backend/core/tests/test_brains.py
index 5c7e571af..5e75bb823 100644
--- a/backend/core/tests/test_brains.py
+++ b/backend/core/tests/test_brains.py
@@ -29,7 +29,7 @@ def test_create_brain(client, api_key):
     payload = {
         "name": random_brain_name,
         "status": "public",
-        "model": "gpt-3.5-turbo-0613",
+        "model": "gpt-3.5-turbo",
         "temperature": 0,
         "max_tokens": 256,
         "file_sha1": "",
@@ -173,7 +173,7 @@ def test_set_as_default_brain_endpoint(client, api_key):
     payload = {
         "name": random_brain_name,
         "status": "public",
-        "model": "gpt-3.5-turbo-0613",
+        "model": "gpt-3.5-turbo",
         "temperature": 0,
         "max_tokens": 256,
     }
diff --git a/backend/core/tests/test_chats.py b/backend/core/tests/test_chats.py
index 567a8660b..c2523bc84 100644
--- a/backend/core/tests/test_chats.py
+++ b/backend/core/tests/test_chats.py
@@ -50,7 +50,7 @@ def test_create_chat_and_talk(client, api_key):
     response = client.post(
         f"/chat/{chat_id}/question?brain_id={default_brain_id}",
         json={
-            "model": "gpt-3.5-turbo-0613",
+            "model": "gpt-3.5-turbo",
             "question": "Hello, how are you?",
             "temperature": "0",
             "max_tokens": "256",
@@ -100,7 +100,7 @@ def test_create_chat_and_talk_with_no_brain(client, api_key):
     response = client.post(
         f"/chat/{chat_id}/question?brain_id=",
         json={
-            "model": "gpt-3.5-turbo-0613",
+            "model": "gpt-3.5-turbo",
             "question": "Hello, how are you?",
             "temperature": "0",
             "max_tokens": "256",
diff --git a/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/SettingsTab.tsx b/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/SettingsTab.tsx
index c1f4cb2f8..7babf96dd 100644
--- a/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/SettingsTab.tsx
+++ b/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/SettingsTab.tsx
@@ -10,8 +10,11 @@ import Button from "@/lib/components/ui/Button";
 import { Divider } from "@/lib/components/ui/Divider";
 import Field from "@/lib/components/ui/Field";
 import { TextArea } from "@/lib/components/ui/TextArea";
-import { models, paidModels } from "@/lib/context/BrainConfigProvider/types";
-import { defineMaxTokens } from "@/lib/helpers/defineMexTokens";
+import {
+  freeModels,
+  paidModels,
+} from "@/lib/context/BrainConfigProvider/types";
+import { defineMaxTokens } from "@/lib/helpers/defineMaxTokens";
 
 import { PublicPrompts } from "./components/PublicPrompts/PublicPrompts";
 import { useSettingsTab } from "./hooks/useSettingsTab";
@@ -99,7 +102,7 @@ export const SettingsTab = ({ brainId }: SettingsTabProps): JSX.Element => {
           {...register("model")}
           className="px-5 py-2 dark:bg-gray-700 bg-gray-200 rounded-md"
         >
-          {(openAiKey !== undefined ? paidModels : models).map(
+          {(openAiKey !== undefined ? paidModels : freeModels).map(
             (availableModel) => (
               <option value={availableModel} key={availableModel}>
                 {availableModel}
diff --git a/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/hooks/useSettingsTab.ts b/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/hooks/useSettingsTab.ts
index 4189fe6fb..d1cba6372 100644
--- a/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/hooks/useSettingsTab.ts
+++ b/frontend/app/brains-management/[brainId]/components/BrainManagementTabs/components/SettingsTab/hooks/useSettingsTab.ts
@@ -11,7 +11,7 @@ import { usePromptApi } from "@/lib/api/prompt/usePromptApi";
 import { useBrainConfig } from "@/lib/context/BrainConfigProvider";
 import { useBrainContext } from "@/lib/context/BrainProvider/hooks/useBrainContext";
 import { Brain } from "@/lib/context/BrainProvider/types";
-import { defineMaxTokens } from "@/lib/helpers/defineMexTokens";
+import { defineMaxTokens } from "@/lib/helpers/defineMaxTokens";
 import { useToast } from "@/lib/hooks";
 
 type UseSettingsTabProps = {
@@ -317,7 +317,7 @@ export const useSettingsTab = ({ brainId }: UseSettingsTabProps) => {
   return {
     handleSubmit,
     register,
-    openAiKey,
+    openAiKey: openAiKey === "" ? undefined : openAiKey,
     model,
     temperature,
     maxTokens,
diff --git a/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/ConfigModal.tsx b/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/ConfigModal.tsx
index c8c71ab35..ed812a473 100644
--- a/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/ConfigModal.tsx
+++ b/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/ConfigModal.tsx
@@ -3,8 +3,8 @@ import { MdCheck, MdSettings } from "react-icons/md";
 
 import Button from "@/lib/components/ui/Button";
 import { Modal } from "@/lib/components/ui/Modal";
-import { models } from "@/lib/context/BrainConfigProvider/types";
-import { defineMaxTokens } from "@/lib/helpers/defineMexTokens";
+import { freeModels } from "@/lib/context/BrainConfigProvider/types";
+import { defineMaxTokens } from "@/lib/helpers/defineMaxTokens";
 
 import { useConfigModal } from "./hooks/useConfigModal";
 
@@ -56,7 +56,7 @@ export const ConfigModal = ({ chatId }: { chatId?: string }): JSX.Element => {
             {...register("model")}
             className="px-5 py-2 dark:bg-gray-700 bg-gray-200 rounded-md"
           >
-            {models.map((availableModel) => (
+            {freeModels.map((availableModel) => (
               <option value={availableModel} key={availableModel}>
                 {availableModel}
               </option>
@@ -85,7 +85,7 @@ export const ConfigModal = ({ chatId }: { chatId?: string }): JSX.Element => {
           <input
             type="range"
             min="10"
-            max={defineMaxTokens(model ?? "gpt-3.5-turbo-0613")}
+            max={defineMaxTokens(model ?? "gpt-3.5-turbo")}
             value={maxTokens}
             {...register("maxTokens")}
           />
diff --git a/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/hooks/useConfigModal.ts b/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/hooks/useConfigModal.ts
index 506a7bc6e..2fd85cccd 100644
--- a/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/hooks/useConfigModal.ts
+++ b/frontend/app/chat/[chatId]/components/ChatInput/components/ConfigModal/hooks/useConfigModal.ts
@@ -10,7 +10,7 @@ import {
 import { useBrainConfig } from "@/lib/context/BrainConfigProvider";
 import { useBrainContext } from "@/lib/context/BrainProvider/hooks/useBrainContext";
 import { ChatConfig } from "@/lib/context/ChatProvider/types";
-import { defineMaxTokens } from "@/lib/helpers/defineMexTokens";
+import { defineMaxTokens } from "@/lib/helpers/defineMaxTokens";
 import { useToast } from "@/lib/hooks";
 
 // eslint-disable-next-line @typescript-eslint/explicit-module-boundary-types
diff --git a/frontend/lib/api/brain/__tests__/useBrainApi.test.ts b/frontend/lib/api/brain/__tests__/useBrainApi.test.ts
index e2ee7c588..4d37e7991 100644
--- a/frontend/lib/api/brain/__tests__/useBrainApi.test.ts
+++ b/frontend/lib/api/brain/__tests__/useBrainApi.test.ts
@@ -66,7 +66,7 @@ describe("useBrainApi", () => {
       name: "Test Brain",
       description: "This is a description",
       status: "public",
-      model: "gpt-3.5-turbo-0613",
+      model: "gpt-3.5-turbo",
       temperature: 0.0,
       max_tokens: 256,
       openai_api_key: "123",
@@ -217,7 +217,7 @@ describe("useBrainApi", () => {
       name: "Test Brain",
       description: "This is a description",
       status: "public",
-      model: "gpt-3.5-turbo-0613",
+      model: "gpt-3.5-turbo",
       temperature: 0.0,
       max_tokens: 256,
       openai_api_key: "123",
diff --git a/frontend/lib/components/AddBrainModal/AddBrainModal.tsx b/frontend/lib/components/AddBrainModal/AddBrainModal.tsx
index e5c8efc3a..4498867a8 100644
--- a/frontend/lib/components/AddBrainModal/AddBrainModal.tsx
+++ b/frontend/lib/components/AddBrainModal/AddBrainModal.tsx
@@ -7,8 +7,11 @@ import { PublicPrompts } from "@/app/brains-management/[brainId]/components/Brai
 import Button from "@/lib/components/ui/Button";
 import Field from "@/lib/components/ui/Field";
 import { Modal } from "@/lib/components/ui/Modal";
-import { models, paidModels } from "@/lib/context/BrainConfigProvider/types";
-import { defineMaxTokens } from "@/lib/helpers/defineMexTokens";
+import {
+  freeModels,
+  paidModels,
+} from "@/lib/context/BrainConfigProvider/types";
+import { defineMaxTokens } from "@/lib/helpers/defineMaxTokens";
 
 import { useAddBrainModal } from "./hooks/useAddBrainModal";
 import { Divider } from "../ui/Divider";
@@ -84,7 +87,7 @@ export const AddBrainModal = (): JSX.Element => {
             {...register("model")}
             className="px-5 py-2 dark:bg-gray-700 bg-gray-200 rounded-md"
           >
-            {(openAiKey !== undefined ? paidModels : models).map(
+            {(openAiKey !== undefined ? paidModels : freeModels).map(
               (availableModel) => (
                 <option value={availableModel} key={availableModel}>
                   {availableModel}
diff --git a/frontend/lib/components/AddBrainModal/hooks/useAddBrainModal.ts b/frontend/lib/components/AddBrainModal/hooks/useAddBrainModal.ts
index 3c120cc28..0b4d94c20 100644
--- a/frontend/lib/components/AddBrainModal/hooks/useAddBrainModal.ts
+++ b/frontend/lib/components/AddBrainModal/hooks/useAddBrainModal.ts
@@ -8,7 +8,7 @@ import { useBrainApi } from "@/lib/api/brain/useBrainApi";
 import { usePromptApi } from "@/lib/api/prompt/usePromptApi";
 import { useBrainConfig } from "@/lib/context/BrainConfigProvider";
 import { useBrainContext } from "@/lib/context/BrainProvider/hooks/useBrainContext";
-import { defineMaxTokens } from "@/lib/helpers/defineMexTokens";
+import { defineMaxTokens } from "@/lib/helpers/defineMaxTokens";
 import { useToast } from "@/lib/hooks";
 
 // eslint-disable-next-line @typescript-eslint/explicit-module-boundary-types
@@ -145,7 +145,7 @@ export const useAddBrainModal = () => {
     setIsShareModalOpen,
     handleSubmit,
     register,
-    openAiKey,
+    openAiKey: openAiKey === "" ? undefined : openAiKey,
     model,
     temperature,
     maxTokens,
diff --git a/frontend/lib/context/BrainConfigProvider/brain-config-provider.tsx b/frontend/lib/context/BrainConfigProvider/brain-config-provider.tsx
index 5d1018d26..3301c60b5 100644
--- a/frontend/lib/context/BrainConfigProvider/brain-config-provider.tsx
+++ b/frontend/lib/context/BrainConfigProvider/brain-config-provider.tsx
@@ -15,7 +15,7 @@ export const BrainConfigContext = createContext<
 >(undefined);
 
 const defaultBrainConfig: BrainConfig = {
-  model: "gpt-3.5-turbo-0613",
+  model: "gpt-3.5-turbo",
   temperature: 0,
   maxTokens: 256,
   keepLocal: true,
diff --git a/frontend/lib/context/BrainConfigProvider/mocks/BrainConfigProviderMock.tsx b/frontend/lib/context/BrainConfigProvider/mocks/BrainConfigProviderMock.tsx
index 34a26ecfe..f6e90fa16 100644
--- a/frontend/lib/context/BrainConfigProvider/mocks/BrainConfigProviderMock.tsx
+++ b/frontend/lib/context/BrainConfigProvider/mocks/BrainConfigProviderMock.tsx
@@ -13,7 +13,7 @@ export const BrainConfigProviderMock = ({
     <BrainConfigContextMock.Provider
       value={{
         config: {
-          model: "gpt-3.5-turbo-0613",
+          model: "gpt-3.5-turbo",
           temperature: 0,
           maxTokens: 256,
           keepLocal: true,
diff --git a/frontend/lib/context/BrainConfigProvider/types.ts b/frontend/lib/context/BrainConfigProvider/types.ts
index 99a1cf308..5b74a2fc7 100644
--- a/frontend/lib/context/BrainConfigProvider/types.ts
+++ b/frontend/lib/context/BrainConfigProvider/types.ts
@@ -21,19 +21,9 @@ export type BrainConfigContextType = {
   resetConfig: () => void;
 };
 
-// export const openAiModels = ["gpt-3.5-turbo", "gpt-4"] as const; ## TODO activate GPT4 when not in demo mode
+export const openAiFreeModels = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k"] as const;
 
-export const openAiModels = [
-  "gpt-3.5-turbo",
-  "gpt-3.5-turbo-0613",
-  "gpt-3.5-turbo-16k",
-] as const;
-export const openAiPaidModels = [
-  "gpt-3.5-turbo-0613",
-  "gpt-3.5-turbo-16k",
-  "gpt-4",
-  "gpt-4-0613",
-] as const;
+export const openAiPaidModels = [...openAiFreeModels, "gpt-4"] as const;
 
 export const anthropicModels = [
   // "claude-v1",
@@ -47,14 +37,14 @@ export const googleModels = [
 ] as const; // TODO activate when not in demo mode
 
 // export const googleModels = [] as const;
-export const models = [
-  ...openAiModels,
-  ...anthropicModels,
-  ...googleModels,
+export const freeModels = [
+  ...openAiFreeModels,
+  // ...anthropicModels,
+  // ...googleModels,
 ] as const;
 
 export const paidModels = [...openAiPaidModels] as const;
 
 export type PaidModels = (typeof paidModels)[number];
 
-export type Model = (typeof models)[number];
+export type Model = (typeof freeModels)[number];
diff --git a/frontend/lib/helpers/defineMexTokens.ts b/frontend/lib/helpers/defineMaxTokens.ts
similarity index 83%
rename from frontend/lib/helpers/defineMexTokens.ts
rename to frontend/lib/helpers/defineMaxTokens.ts
index 18c9319f9..35f7bb807 100644
--- a/frontend/lib/helpers/defineMexTokens.ts
+++ b/frontend/lib/helpers/defineMaxTokens.ts
@@ -3,14 +3,12 @@ import { Model, PaidModels } from "../context/BrainConfigProvider/types";
 export const defineMaxTokens = (model: Model | PaidModels): number => {
   //At the moment is evaluating only models from OpenAI
   switch (model) {
-    case "gpt-3.5-turbo-0613":
+    case "gpt-3.5-turbo":
       return 500;
     case "gpt-3.5-turbo-16k":
       return 2000;
     case "gpt-4":
       return 1000;
-    case "gpt-4-0613":
-      return 100;
     default:
       return 250;
   }