diff --git a/frontend/src/components/LLMSelection/LiteLLMOptions/index.jsx b/frontend/src/components/LLMSelection/LiteLLMOptions/index.jsx
index 34324859..8ed8aefd 100644
--- a/frontend/src/components/LLMSelection/LiteLLMOptions/index.jsx
+++ b/frontend/src/components/LLMSelection/LiteLLMOptions/index.jsx
@@ -40,7 +40,7 @@ export default function LiteLLMOptions({ settings }) {
             type="number"
             name="LiteLLMTokenLimit"
             className="border-none bg-theme-settings-input-bg text-white placeholder:text-theme-settings-input-placeholder text-sm rounded-lg focus:outline-primary-button active:outline-primary-button outline-none block w-full p-2.5"
-            placeholder="4096"
+            placeholder="8192"
             min={1}
             onScroll={(e) => e.target.blur()}
             defaultValue={settings?.LiteLLMTokenLimit}
diff --git a/server/utils/AiProviders/liteLLM/index.js b/server/utils/AiProviders/liteLLM/index.js
index 5ff8bbe5..5fa1cb35 100644
--- a/server/utils/AiProviders/liteLLM/index.js
+++ b/server/utils/AiProviders/liteLLM/index.js
@@ -22,7 +22,7 @@ class LiteLLM {
       apiKey: process.env.LITE_LLM_API_KEY ?? null,
     });
     this.model = modelPreference ?? process.env.LITE_LLM_MODEL_PREF ?? null;
-    this.maxTokens = process.env.LITE_LLM_MODEL_TOKEN_LIMIT ?? 1024;
+
     if (!this.model) throw new Error("LiteLLM must have a valid model set.");
     this.limits = {
       history: this.promptWindowLimit() * 0.15,
@@ -132,7 +132,6 @@ class LiteLLM {
           model: this.model,
           messages,
           temperature,
-          max_tokens: parseInt(this.maxTokens), // LiteLLM requires int
         })
         .catch((e) => {
           throw new Error(e.message);
@@ -168,7 +167,6 @@ class LiteLLM {
         stream: true,
         messages,
         temperature,
-        max_tokens: parseInt(this.maxTokens), // LiteLLM requires int
       }),
       messages,
       runPromptTokenCalculation: true,