diff --git a/dist/index.js b/dist/index.js
index a6f49664..4e563a51 100644
--- a/dist/index.js
+++ b/dist/index.js
@@ -6525,21 +6525,28 @@ class TokenLimits {
     knowledgeCutOff;
     constructor(model = 'gpt-3.5-turbo') {
         this.knowledgeCutOff = '2021-09-01';
-        if (model === 'gpt-4-32k') {
-            this.maxTokens = 32600;
-            this.responseTokens = 4000;
-        }
-        else if (model === 'gpt-3.5-turbo-16k') {
-            this.maxTokens = 16300;
-            this.responseTokens = 3000;
-        }
-        else if (model === 'gpt-4') {
-            this.maxTokens = 8000;
-            this.responseTokens = 2000;
-        }
-        else {
-            this.maxTokens = 4000;
-            this.responseTokens = 1000;
+        switch (model) {
+            case 'gpt-4-1106-preview':
+                this.maxTokens = 128000;
+                this.responseTokens = 4000;
+                this.knowledgeCutOff = '2023-04-01';
+                break;
+            case 'gpt-4':
+                this.maxTokens = 8000;
+                this.responseTokens = 2000;
+                break;
+            case 'gpt-4-32k':
+                this.maxTokens = 32600;
+                this.responseTokens = 4000;
+                break;
+            case 'gpt-3.5-turbo-16k':
+                this.maxTokens = 16300;
+                this.responseTokens = 3000;
+                break;
+            default:
+                this.maxTokens = 4000;
+                this.responseTokens = 1000;
+                break;
         }
         // provide some margin for the request tokens
         this.requestTokens = this.maxTokens - this.responseTokens - 100;
diff --git a/src/limits.ts b/src/limits.ts
index aca807f6..cd95a2ce 100644
--- a/src/limits.ts
+++ b/src/limits.ts
@@ -6,18 +6,28 @@ export class TokenLimits {
 
   constructor(model = 'gpt-3.5-turbo') {
     this.knowledgeCutOff = '2021-09-01'
-    if (model === 'gpt-4-32k') {
-      this.maxTokens = 32600
-      this.responseTokens = 4000
-    } else if (model === 'gpt-3.5-turbo-16k') {
-      this.maxTokens = 16300
-      this.responseTokens = 3000
-    } else if (model === 'gpt-4') {
-      this.maxTokens = 8000
-      this.responseTokens = 2000
-    } else {
-      this.maxTokens = 4000
-      this.responseTokens = 1000
+    switch (model) {
+      case 'gpt-4-1106-preview':
+        this.maxTokens = 128000
+        this.responseTokens = 4000
+        this.knowledgeCutOff = '2023-04-01'
+        break
+      case 'gpt-4':
+        this.maxTokens = 8000
+        this.responseTokens = 2000
+        break
+      case 'gpt-4-32k':
+        this.maxTokens = 32600
+        this.responseTokens = 4000
+        break
+      case 'gpt-3.5-turbo-16k':
+        this.maxTokens = 16300
+        this.responseTokens = 3000
+        break
+      default:
+        this.maxTokens = 4000
+        this.responseTokens = 1000
+        break
     }
     // provide some margin for the request tokens
     this.requestTokens = this.maxTokens - this.responseTokens - 100