diff --git a/app/client/platforms/NewStuffLLMs.ts b/app/client/platforms/NewStuffLLMs.ts
index a08eae9f416..8b548b6674a 100644
--- a/app/client/platforms/NewStuffLLMs.ts
+++ b/app/client/platforms/NewStuffLLMs.ts
@@ -14,7 +14,6 @@ import {
  * 
  * @param model - The model name.
  * @param max_tokens - The maximum number of tokens.
- * @param system_fingerprint - The system fingerprint.
  * @param useMaxTokens - Indicates whether to use the maximum number of tokens.
  * @returns An object containing the configuration for new features:
  *   - max_tokens: The maximum number of tokens.
@@ -27,12 +26,10 @@ import {
 export function getNewStuff(
     model: string,
     max_tokens?: number,
-    system_fingerprint?: string,
     useMaxTokens: boolean = true,
 ): {
     max_tokens?: number;
     maxOutputTokens?: number; // This is the same as maxTokens but for Google AI
-    system_fingerprint?: string;
     isNewModel: boolean;
     payloadType: 'chat' | 'image';
     isDalle: boolean;
@@ -52,7 +49,6 @@ export function getNewStuff(
         return {
             max_tokens: tokens,
             maxOutputTokens: tokens, // Assign the same value to maxOutputTokens
-            system_fingerprint: system_fingerprint ?? modelConfig.system_fingerprint,
             isNewModel: true,
             payloadType,
             isDalle,
diff --git a/app/client/platforms/google.ts b/app/client/platforms/google.ts
index 9d9e9762bd7..695e237a8fc 100644
--- a/app/client/platforms/google.ts
+++ b/app/client/platforms/google.ts
@@ -161,7 +161,6 @@ export class GeminiProApi implements LLMApi {
     const { max_tokens } = getNewStuff(
       options.config.model,
       chatConfig.max_tokens,
-      chatConfig.system_fingerprint,
       chatConfig.useMaxTokens,
     );
 
diff --git a/app/client/platforms/openai.ts b/app/client/platforms/openai.ts
index 36d594fb32b..9c5c10d2f8c 100644
--- a/app/client/platforms/openai.ts
+++ b/app/client/platforms/openai.ts
@@ -187,10 +187,9 @@ export class ChatGPTApi implements LLMApi {
      * @example : A Best Picture of Andromeda Galaxy
      */
     const actualModel = getModelForInstructVersion(modelConfig.model);
-    const { max_tokens, system_fingerprint } = getNewStuff(
+    const { max_tokens } = getNewStuff(
       modelConfig.model,
       modelConfig.max_tokens,
-      modelConfig.system_fingerprint,
       modelConfig.useMaxTokens,
     );
 
diff --git a/app/masks/en.ts b/app/masks/en.ts
index 287189769e4..e7779c4c531 100644
--- a/app/masks/en.ts
+++ b/app/masks/en.ts
@@ -25,7 +25,6 @@ export const EN_MASKS: BuiltinMask[] = [
       quality: "hd",
       size: "1024x1024",
       style: "vivid",
-      system_fingerprint: "",
       sendMemory: true,
       useMaxTokens: false,
       historyMessageCount: 10,
@@ -60,7 +59,6 @@ export const EN_MASKS: BuiltinMask[] = [
       quality: "hd",
       size: "1024x1024",
       style: "vivid",
-      system_fingerprint: "",
       sendMemory: true,
       historyMessageCount: 10,
       compressMessageLengthThreshold: 5000,
diff --git a/app/store/config.ts b/app/store/config.ts
index c77edc667c5..bcce841a1ba 100644
--- a/app/store/config.ts
+++ b/app/store/config.ts
@@ -80,7 +80,6 @@ export const DEFAULT_CONFIG = {
      * `Natural` causes the model to produce more natural, less hyper-real looking images. 
      */
     style: "vivid", // Only DALL·E-3 for DALL·E-2 not not really needed
-    system_fingerprint: "",
     sendMemory: true,
     useMaxTokens: false,
     historyMessageCount: 4,
@@ -260,15 +259,6 @@ export const useAppConfig = createPersistStore(
         };
       }
 
-      // In the wilds 🚀 (still wip because it confusing for LLM + Generative AI Method)
-
-      if (version < 4.2) {
-        state.modelConfig = {
-          ...state.modelConfig,
-          system_fingerprint: "",
-        };
-      }
-
       // Speed Animation default is 30, Lower values will result in faster animation
 
       if (version < 4.3) {