diff --git a/server/utils/AiProviders/anthropic/index.js b/server/utils/AiProviders/anthropic/index.js
index a5f31351..fd6a5504 100644
--- a/server/utils/AiProviders/anthropic/index.js
+++ b/server/utils/AiProviders/anthropic/index.js
@@ -172,6 +172,7 @@ class AnthropicLLM {
           outputTps: completionTokens / result.duration,
           duration: result.duration,
           model: this.model,
+          provider: this.className,
           timestamp: new Date(),
         },
       };
@@ -194,6 +195,7 @@ class AnthropicLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/apipie/index.js b/server/utils/AiProviders/apipie/index.js
index 8a807c5a..6eb0629d 100644
--- a/server/utils/AiProviders/apipie/index.js
+++ b/server/utils/AiProviders/apipie/index.js
@@ -221,6 +221,7 @@ class ApiPieLLM {
           (result.output.usage?.completion_tokens || 0) / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -242,6 +243,7 @@ class ApiPieLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/azureOpenAi/index.js b/server/utils/AiProviders/azureOpenAi/index.js
index ba825eea..a73e3a80 100644
--- a/server/utils/AiProviders/azureOpenAi/index.js
+++ b/server/utils/AiProviders/azureOpenAi/index.js
@@ -15,6 +15,7 @@ class AzureOpenAiLLM {
     if (!process.env.AZURE_OPENAI_KEY)
       throw new Error("No Azure API key was set.");
 
+    this.className = "AzureOpenAiLLM";
     this.openai = new OpenAI({
       apiKey: process.env.AZURE_OPENAI_KEY,
       baseURL: AzureOpenAiLLM.formatBaseUrl(process.env.AZURE_OPENAI_ENDPOINT),
@@ -175,6 +176,7 @@ class AzureOpenAiLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -197,6 +199,7 @@ class AzureOpenAiLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/bedrock/index.js b/server/utils/AiProviders/bedrock/index.js
index 119f3e88..6dc7de6e 100644
--- a/server/utils/AiProviders/bedrock/index.js
+++ b/server/utils/AiProviders/bedrock/index.js
@@ -72,6 +72,7 @@ class AWSBedrockLLM {
         throw new Error(`Required environment variable ${envVar} is not set.`);
     }
 
+    this.className = "AWSBedrockLLM";
     this.model =
       modelPreference || process.env.AWS_BEDROCK_LLM_MODEL_PREFERENCE;
 
@@ -448,6 +449,7 @@ class AWSBedrockLLM {
         outputTps: outputTps,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -493,6 +495,7 @@ class AWSBedrockLLM {
         messages,
         runPromptTokenCalculation: false,
         modelTag: this.model,
+        provider: this.className,
       });
       return measuredStreamRequest;
     } catch (e) {
diff --git a/server/utils/AiProviders/cohere/index.js b/server/utils/AiProviders/cohere/index.js
index aaf7a258..ef14d4c6 100644
--- a/server/utils/AiProviders/cohere/index.js
+++ b/server/utils/AiProviders/cohere/index.js
@@ -125,6 +125,7 @@ class CohereLLM {
         outputTps: completionTokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -143,6 +144,7 @@ class CohereLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/cometapi/index.js b/server/utils/AiProviders/cometapi/index.js
index c9cb74b2..85032ac4 100644
--- a/server/utils/AiProviders/cometapi/index.js
+++ b/server/utils/AiProviders/cometapi/index.js
@@ -226,6 +226,7 @@ class CometApiLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -247,6 +248,7 @@ class CometApiLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/deepseek/index.js b/server/utils/AiProviders/deepseek/index.js
index 136af490..0521d198 100644
--- a/server/utils/AiProviders/deepseek/index.js
+++ b/server/utils/AiProviders/deepseek/index.js
@@ -131,6 +131,7 @@ class DeepSeekLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -152,6 +153,7 @@ class DeepSeekLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/dellProAiStudio/index.js b/server/utils/AiProviders/dellProAiStudio/index.js
index f8dc11f8..1c887d5b 100644
--- a/server/utils/AiProviders/dellProAiStudio/index.js
+++ b/server/utils/AiProviders/dellProAiStudio/index.js
@@ -166,6 +166,7 @@ class DellProAiStudioLLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -187,6 +188,7 @@ class DellProAiStudioLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/dockerModelRunner/index.js b/server/utils/AiProviders/dockerModelRunner/index.js
index 27faa6a1..8febe010 100644
--- a/server/utils/AiProviders/dockerModelRunner/index.js
+++ b/server/utils/AiProviders/dockerModelRunner/index.js
@@ -26,6 +26,7 @@ class DockerModelRunnerLLM {
     if (!process.env.DOCKER_MODEL_RUNNER_LLM_MODEL_PREF && !modelPreference)
       throw new Error("No Docker Model Runner Model Pref was set.");
 
+    this.className = "DockerModelRunnerLLM";
     this.dmr = new OpenAIApi({
       baseURL: parseDockerModelRunnerEndpoint(
         process.env.DOCKER_MODEL_RUNNER_BASE_PATH
@@ -173,6 +174,7 @@ class DockerModelRunnerLLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -194,6 +196,7 @@ class DockerModelRunnerLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/fireworksAi/index.js b/server/utils/AiProviders/fireworksAi/index.js
index 6f3ec426..48cb08cf 100644
--- a/server/utils/AiProviders/fireworksAi/index.js
+++ b/server/utils/AiProviders/fireworksAi/index.js
@@ -164,6 +164,7 @@ class FireworksAiLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -185,6 +186,7 @@ class FireworksAiLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/foundry/index.js b/server/utils/AiProviders/foundry/index.js
index ed91c717..b503e212 100644
--- a/server/utils/AiProviders/foundry/index.js
+++ b/server/utils/AiProviders/foundry/index.js
@@ -234,6 +234,7 @@ class FoundryLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -256,6 +257,7 @@ class FoundryLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/gemini/index.js b/server/utils/AiProviders/gemini/index.js
index 91f25441..9ac2b9f5 100644
--- a/server/utils/AiProviders/gemini/index.js
+++ b/server/utils/AiProviders/gemini/index.js
@@ -406,6 +406,7 @@ class GeminiLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -425,6 +426,7 @@ class GeminiLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/genericOpenAi/index.js b/server/utils/AiProviders/genericOpenAi/index.js
index ed5fba28..7572a535 100644
--- a/server/utils/AiProviders/genericOpenAi/index.js
+++ b/server/utils/AiProviders/genericOpenAi/index.js
@@ -194,6 +194,7 @@ class GenericOpenAiLLM {
           (result.output?.usage?.completion_tokens || 0) / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -209,9 +210,9 @@ class GenericOpenAiLLM {
         max_tokens: this.maxTokens,
       }),
       messages,
-      // runPromptTokenCalculation: true - There is not way to know if the generic provider connected is returning
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/giteeai/index.js b/server/utils/AiProviders/giteeai/index.js
index e5849f28..8be36e29 100644
--- a/server/utils/AiProviders/giteeai/index.js
+++ b/server/utils/AiProviders/giteeai/index.js
@@ -23,6 +23,7 @@ class GiteeAILLM {
       throw new Error("No Gitee AI API key was set.");
     const { OpenAI: OpenAIApi } = require("openai");
 
+    this.className = "GiteeAILLM";
     this.openai = new OpenAIApi({
       apiKey: process.env.GITEE_AI_API_KEY,
       baseURL: "https://ai.gitee.com/v1",
@@ -48,27 +49,6 @@ class GiteeAILLM {
     console.log(`\x1b[36m[${this.constructor.name}]\x1b[0m ${text}`, ...args);
   }
 
-  // This checks if the .cached_at file has a timestamp that is more than 1Week (in millis)
-  // from the current date. If it is, then we will refetch the API so that all the models are up
-  // to date.
-  #cacheIsStale() {
-    const MAX_STALE = 6.048e8; // 1 Week in MS
-    if (!fs.existsSync(this.cacheAtPath)) return true;
-    const now = Number(new Date());
-    const timestampMs = Number(fs.readFileSync(this.cacheAtPath));
-    return now - timestampMs > MAX_STALE;
-  }
-
-  // This function fetches the models from the GiteeAI API and caches them locally.
-  async #syncModels() {
-    if (fs.existsSync(this.cacheModelPath) && !this.#cacheIsStale())
-      return false;
-
-    this.log("Model cache is not present or stale. Fetching from GiteeAI API.");
-    await giteeAiModels();
-    return;
-  }
-
   models() {
     if (!fs.existsSync(this.cacheModelPath)) return {};
     return safeJsonParse(
@@ -171,6 +151,7 @@ class GiteeAILLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -187,6 +168,7 @@ class GiteeAILLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/groq/index.js b/server/utils/AiProviders/groq/index.js
index a05f6f5b..b697ab13 100644
--- a/server/utils/AiProviders/groq/index.js
+++ b/server/utils/AiProviders/groq/index.js
@@ -11,6 +11,7 @@ class GroqLLM {
   constructor(embedder = null, modelPreference = null) {
     const { OpenAI: OpenAIApi } = require("openai");
     if (!process.env.GROQ_API_KEY) throw new Error("No Groq API key was set.");
+    this.className = "GroqLLM";
 
     this.openai = new OpenAIApi({
       baseURL: "https://api.groq.com/openai/v1",
@@ -204,6 +205,7 @@ class GroqLLM {
           result.output.usage.completion_time,
         duration: result.output.usage.total_time,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -225,6 +227,7 @@ class GroqLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/huggingface/index.js b/server/utils/AiProviders/huggingface/index.js
index f84e0273..2f5dc591 100644
--- a/server/utils/AiProviders/huggingface/index.js
+++ b/server/utils/AiProviders/huggingface/index.js
@@ -14,6 +14,7 @@ class HuggingFaceLLM {
       throw new Error("No HuggingFace Access Token was set.");
     const { OpenAI: OpenAIApi } = require("openai");
 
+    this.className = "HuggingFaceLLM";
     this.openai = new OpenAIApi({
       baseURL: `${process.env.HUGGING_FACE_LLM_ENDPOINT}/v1`,
       apiKey: process.env.HUGGING_FACE_LLM_API_KEY,
@@ -118,6 +119,7 @@ class HuggingFaceLLM {
           (result.output.usage?.completion_tokens || 0) / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -134,6 +136,7 @@ class HuggingFaceLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/koboldCPP/index.js b/server/utils/AiProviders/koboldCPP/index.js
index a973d664..fa349236 100644
--- a/server/utils/AiProviders/koboldCPP/index.js
+++ b/server/utils/AiProviders/koboldCPP/index.js
@@ -161,6 +161,7 @@ class KoboldCPPLLM {
         outputTps: completionTokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -178,6 +179,7 @@ class KoboldCPPLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/liteLLM/index.js b/server/utils/AiProviders/liteLLM/index.js
index 65e20151..5ff8bbe5 100644
--- a/server/utils/AiProviders/liteLLM/index.js
+++ b/server/utils/AiProviders/liteLLM/index.js
@@ -155,6 +155,7 @@ class LiteLLM {
           (result.output.usage?.completion_tokens || 0) / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -170,9 +171,9 @@ class LiteLLM {
         max_tokens: parseInt(this.maxTokens), // LiteLLM requires int
       }),
       messages,
-      // runPromptTokenCalculation: true - We manually count the tokens because they may or may not be provided in the stream
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/lmStudio/index.js b/server/utils/AiProviders/lmStudio/index.js
index 1327dc66..78a5a792 100644
--- a/server/utils/AiProviders/lmStudio/index.js
+++ b/server/utils/AiProviders/lmStudio/index.js
@@ -17,6 +17,7 @@ class LMStudioLLM {
     if (!process.env.LMSTUDIO_BASE_PATH)
       throw new Error("No LMStudio API Base Path was set.");
 
+    this.className = "LMStudioLLM";
     const apiKey = process.env.LMSTUDIO_AUTH_TOKEN ?? null;
     this.lmstudio = new OpenAIApi({
       baseURL: parseLMStudioBasePath(process.env.LMSTUDIO_BASE_PATH), // here is the URL to your LMStudio instance
@@ -240,6 +241,7 @@ class LMStudioLLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -261,6 +263,7 @@ class LMStudioLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/localAi/index.js b/server/utils/AiProviders/localAi/index.js
index 54f061c9..bc723e75 100644
--- a/server/utils/AiProviders/localAi/index.js
+++ b/server/utils/AiProviders/localAi/index.js
@@ -12,6 +12,7 @@ class LocalAiLLM {
     if (!process.env.LOCAL_AI_BASE_PATH)
       throw new Error("No LocalAI Base Path was set.");
 
+    this.className = "LocalAiLLM";
     const { OpenAI: OpenAIApi } = require("openai");
     this.openai = new OpenAIApi({
       baseURL: process.env.LOCAL_AI_BASE_PATH,
@@ -146,6 +147,7 @@ class LocalAiLLM {
         outputTps: completionTokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -167,6 +169,7 @@ class LocalAiLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/mistral/index.js b/server/utils/AiProviders/mistral/index.js
index 89849f04..07298ef9 100644
--- a/server/utils/AiProviders/mistral/index.js
+++ b/server/utils/AiProviders/mistral/index.js
@@ -140,6 +140,7 @@ class MistralLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -161,6 +162,7 @@ class MistralLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/moonshotAi/index.js b/server/utils/AiProviders/moonshotAi/index.js
index 273c7449..17e624f9 100644
--- a/server/utils/AiProviders/moonshotAi/index.js
+++ b/server/utils/AiProviders/moonshotAi/index.js
@@ -137,6 +137,7 @@ class MoonshotAiLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -153,6 +154,7 @@ class MoonshotAiLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/novita/index.js b/server/utils/AiProviders/novita/index.js
index 84b1c783..957605a9 100644
--- a/server/utils/AiProviders/novita/index.js
+++ b/server/utils/AiProviders/novita/index.js
@@ -226,6 +226,7 @@ class NovitaLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -247,6 +248,7 @@ class NovitaLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/nvidiaNim/index.js b/server/utils/AiProviders/nvidiaNim/index.js
index 6ff1dd38..63e309a4 100644
--- a/server/utils/AiProviders/nvidiaNim/index.js
+++ b/server/utils/AiProviders/nvidiaNim/index.js
@@ -185,6 +185,7 @@ class NvidiaNimLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -206,6 +207,7 @@ class NvidiaNimLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/ollama/index.js b/server/utils/AiProviders/ollama/index.js
index cb733e02..e9a71115 100644
--- a/server/utils/AiProviders/ollama/index.js
+++ b/server/utils/AiProviders/ollama/index.js
@@ -312,6 +312,7 @@ class OllamaAILLM {
           result.output.usage.completion_tokens / result.output.usage.duration,
         duration: result.output.usage.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -333,6 +334,7 @@ class OllamaAILLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     }).catch((e) => {
       throw this.#errorHandler(e);
     });
diff --git a/server/utils/AiProviders/openAi/index.js b/server/utils/AiProviders/openAi/index.js
index 2420aa29..55fed492 100644
--- a/server/utils/AiProviders/openAi/index.js
+++ b/server/utils/AiProviders/openAi/index.js
@@ -176,6 +176,7 @@ class OpenAiLLM {
           : 0,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -198,6 +199,7 @@ class OpenAiLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/openRouter/index.js b/server/utils/AiProviders/openRouter/index.js
index 23832700..c8e12748 100644
--- a/server/utils/AiProviders/openRouter/index.js
+++ b/server/utils/AiProviders/openRouter/index.js
@@ -277,6 +277,7 @@ class OpenRouterLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -311,6 +312,7 @@ class OpenRouterLLM {
       // is not available.
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/perplexity/index.js b/server/utils/AiProviders/perplexity/index.js
index 01fc566b..2a1b4f27 100644
--- a/server/utils/AiProviders/perplexity/index.js
+++ b/server/utils/AiProviders/perplexity/index.js
@@ -18,6 +18,7 @@ class PerplexityLLM {
     if (!process.env.PERPLEXITY_API_KEY)
       throw new Error("No Perplexity API key was set.");
 
+    this.className = "PerplexityLLM";
     const { OpenAI: OpenAIApi } = require("openai");
     this.openai = new OpenAIApi({
       baseURL: "https://api.perplexity.ai",
@@ -118,6 +119,7 @@ class PerplexityLLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -139,6 +141,7 @@ class PerplexityLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/ppio/index.js b/server/utils/AiProviders/ppio/index.js
index 81325157..f10ede2e 100644
--- a/server/utils/AiProviders/ppio/index.js
+++ b/server/utils/AiProviders/ppio/index.js
@@ -177,6 +177,7 @@ class PPIOLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -198,6 +199,7 @@ class PPIOLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/privatemode/index.js b/server/utils/AiProviders/privatemode/index.js
index 47e8f80e..7f71ec2b 100644
--- a/server/utils/AiProviders/privatemode/index.js
+++ b/server/utils/AiProviders/privatemode/index.js
@@ -169,6 +169,7 @@ class PrivatemodeLLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -190,6 +191,7 @@ class PrivatemodeLLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/sambanova/index.js b/server/utils/AiProviders/sambanova/index.js
index 49ae1614..4cec536d 100644
--- a/server/utils/AiProviders/sambanova/index.js
+++ b/server/utils/AiProviders/sambanova/index.js
@@ -137,6 +137,7 @@ class SambaNovaLLM {
         outputTps: result.output.usage?.total_tokens_per_sec || 0,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -156,6 +157,7 @@ class SambaNovaLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/textGenWebUI/index.js b/server/utils/AiProviders/textGenWebUI/index.js
index 253f9ef1..7d7cac22 100644
--- a/server/utils/AiProviders/textGenWebUI/index.js
+++ b/server/utils/AiProviders/textGenWebUI/index.js
@@ -151,6 +151,7 @@ class TextGenWebUILLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -167,6 +168,7 @@ class TextGenWebUILLM {
       messages,
       runPromptTokenCalculation: true,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/togetherAi/index.js b/server/utils/AiProviders/togetherAi/index.js
index 9ab5b827..f9571644 100644
--- a/server/utils/AiProviders/togetherAi/index.js
+++ b/server/utils/AiProviders/togetherAi/index.js
@@ -82,6 +82,7 @@ class TogetherAiLLM {
     if (!process.env.TOGETHER_AI_API_KEY)
       throw new Error("No TogetherAI API key was set.");
     const { OpenAI: OpenAIApi } = require("openai");
+    this.className = "TogetherAiLLM";
     this.openai = new OpenAIApi({
       baseURL: "https://api.together.xyz/v1",
       apiKey: process.env.TOGETHER_AI_API_KEY ?? null,
@@ -210,6 +211,7 @@ class TogetherAiLLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -231,6 +233,7 @@ class TogetherAiLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
     return measuredStreamRequest;
   }
diff --git a/server/utils/AiProviders/xai/index.js b/server/utils/AiProviders/xai/index.js
index dbb21dab..ae5eff68 100644
--- a/server/utils/AiProviders/xai/index.js
+++ b/server/utils/AiProviders/xai/index.js
@@ -148,6 +148,7 @@ class XAiLLM {
         outputTps: result.output.usage.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -169,6 +170,7 @@ class XAiLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/AiProviders/zai/index.js b/server/utils/AiProviders/zai/index.js
index be550268..40480897 100644
--- a/server/utils/AiProviders/zai/index.js
+++ b/server/utils/AiProviders/zai/index.js
@@ -137,6 +137,7 @@ class ZAiLLM {
         outputTps: result.output.usage?.completion_tokens / result.duration,
         duration: result.duration,
         model: this.model,
+        provider: this.className,
         timestamp: new Date(),
       },
     };
@@ -153,6 +154,7 @@ class ZAiLLM {
       messages,
       runPromptTokenCalculation: false,
       modelTag: this.model,
+      provider: this.className,
     });
 
     return measuredStreamRequest;
diff --git a/server/utils/helpers/chat/LLMPerformanceMonitor.js b/server/utils/helpers/chat/LLMPerformanceMonitor.js
index 1423c672..e30d300a 100644
--- a/server/utils/helpers/chat/LLMPerformanceMonitor.js
+++ b/server/utils/helpers/chat/LLMPerformanceMonitor.js
@@ -62,6 +62,7 @@ class LLMPerformanceMonitor {
    * @param {Messages} [opts.messages=[]] - the messages sent to the LLM so we can calculate the prompt tokens since most providers do not return this on stream
    * @param {boolean} [opts.runPromptTokenCalculation=true] - whether to run the prompt token calculation to estimate the `prompt_tokens` metric. This is useful for providers that do not return this on stream.
    * @param {string} [opts.modelTag=""] - the tag of the model that was used to generate the stream (eg: gpt-4o, claude-3-5-sonnet, qwen3/72b-instruct, etc.)
+   * @param {string} [opts.provider=""] - the class name of the LLM that was used to generate the stream (eg: OpenAI, Anthropic, LMStudio, ApiPie, etc.)
    * @returns {Promise<MonitoredStream>}
    */
   static async measureStream({
@@ -69,6 +70,7 @@ class LLMPerformanceMonitor {
     messages = [],
     runPromptTokenCalculation = true,
     modelTag = "",
+    provider = "",
   }) {
     const stream = await func;
     stream.start = Date.now();
@@ -80,6 +82,7 @@ class LLMPerformanceMonitor {
       outputTps: 0,
       duration: 0,
       ...(modelTag ? { model: modelTag } : {}),
+      ...(provider ? { provider: provider } : {}),
     };
 
     stream.endMeasurement = (reportedUsage = {}) => {