diff --git a/js/plugins/googleai/src/context-caching/helpers.ts b/js/plugins/googleai/src/context-caching/helpers.ts
index 543c75b37..e7c4bb159 100644
--- a/js/plugins/googleai/src/context-caching/helpers.ts
+++ b/js/plugins/googleai/src/context-caching/helpers.ts
@@ -41,8 +41,6 @@ export function getContentForCache(
     throw new Error('No history provided for context caching');
   }
 
-  logger.info('model version', modelVersion);
-
   const cachedContent: CachedContent = {
     model: modelVersion,
     contents: [],
@@ -55,10 +53,7 @@ export function getContentForCache(
 
   // We split history into two parts: the part that should be cached and the part that should not
   const slicedHistory = chatRequest.history.slice(0, endOfCachedContents);
-  logger.info(
-    'last of cached contents',
-    JSON.stringify(slicedHistory.map((m) => m.role))
-  );
+
   cachedContent.contents = slicedHistory;
 
   let newHistory;
@@ -70,8 +65,6 @@ export function getContentForCache(
   }
   chatRequest.history = newHistory;
 
-  logger.info('new history', JSON.stringify(newHistory.map((m) => m.role)));
-
   if (request.config?.contextCache?.context) {
     cachedContent.systemInstruction = toGeminiSystemInstruction({
       role: 'system',
@@ -140,7 +133,7 @@ export function validateContextCacheRequest(
 ): boolean {
   // Check if contextCache is requested in the config
   if (!request.config?.contextCache) {
-    logger.info('Context caching is not requested');
+    logger.debug('Context caching is not requested');
     return false;
   }
 
@@ -183,13 +176,13 @@ export function validateContextCacheRequest(
     });
   }
 
-  logger.info('Context caching is valid for this request');
+  logger.debug('Context caching is valid for this request');
   // If all checks pass, content should be cached
   return true;
 }
 
 /**
- * Clears ALL
+ * Utility to clear ALL Caches
  * @param cacheManager
  * @param maxPages
  * @param pageSize
diff --git a/js/plugins/googleai/src/context-caching/index.ts b/js/plugins/googleai/src/context-caching/index.ts
index 4321e014a..0a68fa9fd 100644
--- a/js/plugins/googleai/src/context-caching/index.ts
+++ b/js/plugins/googleai/src/context-caching/index.ts
@@ -38,7 +38,6 @@ export async function handleContextCache(
   chatRequest: StartChatParams,
   modelVersion: string
 ): Promise<{ cache: CachedContent; newChatRequest: StartChatParams }> {
-  logger.info('Using context cache feature');
   const cacheManager = new GoogleAICacheManager(apiKey);
 
   const { cachedContent, chatRequest: newChatRequest } = getContentForCache(
@@ -46,21 +45,19 @@ export async function handleContextCache(
     chatRequest,
     modelVersion
   );
-
-  logger.info('Cached content:', cachedContent);
   cachedContent.model = modelVersion;
   const cacheKey = generateCacheKey(cachedContent);
 
   cachedContent.displayName = cacheKey;
-  logger.info(`Generated cache key: ${cacheKey}`);
+  logger.debug(`Generated cache key: ${cacheKey}`);
   let cache = await lookupContextCache(cacheManager, cacheKey);
-  logger.info(`Found cache: ${cache ? 'true' : 'false'}`);
+  logger.debug(`Cache hit: ${cache ? 'true' : 'false'}`);
 
   if (!cache) {
     try {
       logger.debug('No cache found, creating one.');
       cache = await cacheManager.create(cachedContent);
-      logger.info(`Created new cache entry with key: ${cacheKey}`);
+      logger.debug(`Created new cache entry with key: ${cacheKey}`);
     } catch (cacheError) {
       throw new GenkitError({
         status: 'INTERNAL',
diff --git a/js/plugins/googleai/src/gemini.ts b/js/plugins/googleai/src/gemini.ts
index 6a405cac0..954fc086c 100644
--- a/js/plugins/googleai/src/gemini.ts
+++ b/js/plugins/googleai/src/gemini.ts
@@ -580,8 +580,6 @@ export function googleAIModel(
         return fromGeminiCandidate(candidate, jsonMode);
       };
 
-      logger.info('request config', request.config);
-
       let chatRequest = {
         systemInstruction,
         generationConfig,
@@ -618,7 +616,7 @@ export function googleAIModel(
       const client = new GoogleGenerativeAI(apiKey!);
 
       if (cache) {
-        logger.info('Using cached content');
+        logger.debug('Using Context Cache');
         genModel = client.getGenerativeModelFromCachedContent(cache, options);
       } else {
         genModel = client.getGenerativeModel(
@@ -628,7 +626,6 @@ export function googleAIModel(
           options
         );
       }
-      logger.info('created generative model client');
 
       if (streamingCallback) {
         const result = await genModel
@@ -653,7 +650,6 @@ export function googleAIModel(
           custom: response,
         };
       } else {
-        logger.info(chatRequest!.history![0].role);
         const result = await genModel
           .startChat(chatRequest)
           .sendMessage(msg.parts, options);