diff --git a/core/src/commonTest/kotlin/com/xebia/functional/xef/conversation/ConversationSpec.kt b/core/src/commonTest/kotlin/com/xebia/functional/xef/conversation/ConversationSpec.kt
index 4a722b1c4..8f0067550 100644
--- a/core/src/commonTest/kotlin/com/xebia/functional/xef/conversation/ConversationSpec.kt
+++ b/core/src/commonTest/kotlin/com/xebia/functional/xef/conversation/ConversationSpec.kt
@@ -49,7 +49,7 @@ class ConversationSpec :
     }
 
     """"
-      | GPT_3_5_TURBO model has 4097 max context length
+      | GPT_3_5_TURBO model has 16385 max context length
       | when the number of token in the conversation is greater than
       | the space allotted for the message history in the prompt configuration
       | the number of messages in the request must have fewer messages than
@@ -80,7 +80,7 @@ class ConversationSpec :
       val memories = vectorStore.memories(model, conversationId, totalTokens)
 
       // The messages in the request doesn't contain the message response
-      val messagesSizePlusMessageResponse = lastRequest.messages.size + 1
+      val messagesSizePlusMessageResponse = lastRequest.messages.size
 
       messagesSizePlusMessageResponse shouldBeLessThan memories.size
     }
diff --git a/tokenizer/src/commonMain/kotlin/com/xebia/functional/tokenizer/ModelType.kt b/tokenizer/src/commonMain/kotlin/com/xebia/functional/tokenizer/ModelType.kt
index 3c0fee90b..4a4c5f4f4 100644
--- a/tokenizer/src/commonMain/kotlin/com/xebia/functional/tokenizer/ModelType.kt
+++ b/tokenizer/src/commonMain/kotlin/com/xebia/functional/tokenizer/ModelType.kt
@@ -38,6 +38,7 @@ sealed class ModelType(
     val DEFAULT_SPLITTER_MODEL = GPT_3_5_TURBO
     val functionSpecific: List<ModelType> = listOf(
       GPT_3_5_TURBO_0613,
+      GPT_3_5_TURBO_0125,
       GPT_3_5_16K_0613_TURBO_FUNCTIONS,
       GPT_4_32K_0314_FUNCTIONS,
       GPT_4_0613,
@@ -50,6 +51,7 @@ sealed class ModelType(
       GPT_3_5_TURBO,
       GPT_3_5_TURBO_0301,
       GPT_3_5_TURBO_0613,
+      GPT_3_5_TURBO_0125,
       GPT_3_5_TURBO_FUNCTIONS,
       GPT_3_5_TURBO_16_K,
       GPT_3_5_TURBO_16_K_1106,
@@ -103,11 +105,16 @@ sealed class ModelType(
   ) : ModelType(name, encodingType, maxContextLength)
 
   object GPT_3_5_TURBO :
-    ModelType("gpt-3.5-turbo", CL100K_BASE, 4097, tokensPerMessage = 4, tokensPerName = 0, tokenPadding = 5)
+    ModelType("gpt-3.5-turbo", CL100K_BASE, 16385, tokensPerMessage = 4, tokensPerName = 0, tokenPadding = 5)
 
+  object GPT_3_5_TURBO_0125 :
+    ModelType("gpt-3.5-turbo-0125", CL100K_BASE, 16385, tokensPerMessage = 4, tokensPerName = 0, tokenPadding = 5)
+
+  @Deprecated("Use GPT_3_5_TURBO_0125 instead")
   object GPT_3_5_TURBO_0301 :
     ModelType("gpt-3.5-turbo-0301", CL100K_BASE, 4097, tokensPerMessage = 4, tokensPerName = 0, tokenPadding = 5)
 
+  @Deprecated("Use GPT_3_5_TURBO_0125 instead")
   object GPT_3_5_TURBO_0613 :
     ModelType("gpt-3.5-turbo-0613", CL100K_BASE, 4097, tokensPerMessage = 3, tokensPerName = 2, tokenPadding = 5)