diff --git a/app/MindWork AI Studio/Dialogs/ProviderDialog.razor.cs b/app/MindWork AI Studio/Dialogs/ProviderDialog.razor.cs
index 78592b33..822f64ed 100644
--- a/app/MindWork AI Studio/Dialogs/ProviderDialog.razor.cs	
+++ b/app/MindWork AI Studio/Dialogs/ProviderDialog.razor.cs	
@@ -164,7 +164,7 @@ public partial class ProviderDialog : MSGComponentBase, ISecretId
             //
             // We cannot load the API key for self-hosted providers:
             //
-            if (this.DataLLMProvider is LLMProviders.SELF_HOSTED && this.DataHost is not Host.OLLAMA)
+            if (this.DataLLMProvider is LLMProviders.SELF_HOSTED && this.DataHost is not Host.OLLAMA && this.DataHost is not Host.V_LLM)
             {
                 await this.ReloadModels();
                 await base.OnInitializedAsync();
diff --git a/app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs b/app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs
index 1c820baa..2ce11c65 100644
--- a/app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs	
+++ b/app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs	
@@ -285,7 +285,7 @@ public static class LLMProvidersExtensions
         LLMProviders.GWDG => true,
         LLMProviders.HUGGINGFACE => true,
         
-        LLMProviders.SELF_HOSTED => host is Host.OLLAMA,
+        LLMProviders.SELF_HOSTED => host is (Host.OLLAMA or Host.V_LLM),
         
         _ => false,
     };
@@ -322,6 +322,7 @@ public static class LLMProvidersExtensions
 
                 case Host.OLLAMA:
                 case Host.LM_STUDIO:
+                case Host.V_LLM:
                     return true;
             }
         }
diff --git a/app/MindWork AI Studio/Provider/SelfHosted/ChatRequest.cs b/app/MindWork AI Studio/Provider/SelfHosted/ChatRequest.cs
index 74b3f089..db05e365 100644
--- a/app/MindWork AI Studio/Provider/SelfHosted/ChatRequest.cs	
+++ b/app/MindWork AI Studio/Provider/SelfHosted/ChatRequest.cs	
@@ -6,11 +6,8 @@ namespace AIStudio.Provider.SelfHosted;
 /// <param name="Model">Which model to use for chat completion.</param>
 /// <param name="Messages">The chat messages.</param>
 /// <param name="Stream">Whether to stream the chat completion.</param>
-/// <param name="MaxTokens">The maximum number of tokens to generate.</param>
 public readonly record struct ChatRequest(
     string Model,
     IList<Message> Messages,
-    bool Stream,
-    
-    int MaxTokens
+    bool Stream
 );
\ No newline at end of file
diff --git a/app/MindWork AI Studio/Provider/SelfHosted/Host.cs b/app/MindWork AI Studio/Provider/SelfHosted/Host.cs
index c90ecc9a..205c4166 100644
--- a/app/MindWork AI Studio/Provider/SelfHosted/Host.cs	
+++ b/app/MindWork AI Studio/Provider/SelfHosted/Host.cs	
@@ -7,4 +7,5 @@ public enum Host
     LM_STUDIO,
     LLAMACPP,
     OLLAMA,
+    V_LLM,
 }
\ No newline at end of file
diff --git a/app/MindWork AI Studio/Provider/SelfHosted/HostExtensions.cs b/app/MindWork AI Studio/Provider/SelfHosted/HostExtensions.cs
index a4e29648..571e665a 100644
--- a/app/MindWork AI Studio/Provider/SelfHosted/HostExtensions.cs	
+++ b/app/MindWork AI Studio/Provider/SelfHosted/HostExtensions.cs	
@@ -9,6 +9,7 @@ public static class HostExtensions
         Host.LM_STUDIO => "LM Studio",
         Host.LLAMACPP => "llama.cpp",
         Host.OLLAMA => "ollama",
+        Host.V_LLM => "vLLM",
 
         _ => "Unknown",
     };
@@ -29,6 +30,7 @@ public static class HostExtensions
         {
             case Host.LM_STUDIO:
             case Host.OLLAMA:
+            case Host.V_LLM:
                 return true;
             
             default:
diff --git a/app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs b/app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs
index a2e997f9..3bba1ccf 100644
--- a/app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs	
+++ b/app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs	
@@ -58,8 +58,7 @@ public sealed class ProviderSelfHosted(ILogger logger, Host host, string hostnam
             }).ToList()],
             
             // Right now, we only support streaming completions:
-            Stream = true,
-            MaxTokens = -1,
+            Stream = true
         }, JSON_SERIALIZER_OPTIONS);
 
         async Task<HttpRequestMessage> RequestBuilder()
@@ -101,6 +100,7 @@ public sealed class ProviderSelfHosted(ILogger logger, Host host, string hostnam
             
                 case Host.LM_STUDIO:
                 case Host.OLLAMA:
+                case Host.V_LLM:
                     return await this.LoadModels(["embed"], [], token, apiKeyProvisional);
             }
 
@@ -127,6 +127,7 @@ public sealed class ProviderSelfHosted(ILogger logger, Host host, string hostnam
             {
                 case Host.LM_STUDIO:
                 case Host.OLLAMA:
+                case Host.V_LLM:
                     return await this.LoadModels([], ["embed"], token, apiKeyProvisional);
             }