diff --git a/packages/datadog-plugin-google-cloud-vertexai/src/tracing.js b/packages/datadog-plugin-google-cloud-vertexai/src/tracing.js
index 8b0fb04f696..66411a2f276 100644
--- a/packages/datadog-plugin-google-cloud-vertexai/src/tracing.js
+++ b/packages/datadog-plugin-google-cloud-vertexai/src/tracing.js
@@ -7,7 +7,6 @@ const makeUtilities = require('../../dd-trace/src/plugins/util/llm')
 
 const {
   extractModel,
-  extractSystemInstructions
 } = require('./utils')
 
 class GoogleCloudVertexAITracingPlugin extends TracingPlugin {
@@ -47,14 +46,6 @@ class GoogleCloudVertexAITracingPlugin extends TracingPlugin {
     const span = ctx.currentStore?.span
     if (!span) return
 
-    const { result } = ctx
-
-    const response = result?.response
-    if (response) {
-      const tags = this.tagResponse(response, span)
-      span.addTags(tags)
-    }
-
     span.finish()
   }
 
@@ -73,129 +64,12 @@ class GoogleCloudVertexAITracingPlugin extends TracingPlugin {
       'vertexai.request.model': model
     }
 
-    const history = instance.historyInternal
-
-    let contents = typeof request === 'string' || Array.isArray(request) ? request : request.contents
-    if (history) {
-      contents = [...history, ...(Array.isArray(contents) ? contents : [contents])]
-    }
-
     const generationConfig = instance.generationConfig || {}
     for (const key of Object.keys(generationConfig)) {
       const transformedKey = key.replaceAll(/([a-z0-9])([A-Z])/g, '$1_$2').toLowerCase()
       tags[`vertexai.request.generation_config.${transformedKey}`] = JSON.stringify(generationConfig[key])
     }
 
-    if (stream) {
-      tags['vertexai.request.stream'] = true
-    }
-
-    if (!this.isPromptCompletionSampled(span)) return tags
-
-    const systemInstructions = extractSystemInstructions(instance)
-
-    for (const [idx, systemInstruction] of systemInstructions.entries()) {
-      tags[`vertexai.request.system_instruction.${idx}.text`] = systemInstruction
-    }
-
-    if (typeof contents === 'string') {
-      tags['vertexai.request.contents.0.text'] = contents
-      return tags
-    }
-
-    for (const [contentIdx, content] of contents.entries()) {
-      this.tagRequestContent(tags, content, contentIdx)
-    }
-
-    return tags
-  }
-
-  tagRequestPart (part, tags, partIdx, contentIdx) {
-    tags[`vertexai.request.contents.${contentIdx}.parts.${partIdx}.text`] = this.normalize(part.text)
-
-    const functionCall = part.functionCall
-    const functionResponse = part.functionResponse
-
-    if (functionCall) {
-      tags[`vertexai.request.contents.${contentIdx}.parts.${partIdx}.function_call.name`] = functionCall.name
-      tags[`vertexai.request.contents.${contentIdx}.parts.${partIdx}.function_call.args`] =
-              this.normalize(JSON.stringify(functionCall.args))
-    }
-    if (functionResponse) {
-      tags[`vertexai.request.contents.${contentIdx}.parts.${partIdx}.function_response.name`] =
-              functionResponse.name
-      tags[`vertexai.request.contents.${contentIdx}.parts.${partIdx}.function_response.response`] =
-              this.normalize(JSON.stringify(functionResponse.response))
-    }
-  }
-
-  tagRequestContent (tags, content, contentIdx) {
-    if (typeof content === 'string') {
-      tags[`vertexai.request.contents.${contentIdx}.text`] = this.normalize(content)
-      return
-    }
-
-    if (content.text || content.functionCall || content.functionResponse) {
-      this.tagRequestPart(content, tags, 0, contentIdx)
-      return
-    }
-
-    const { role, parts } = content
-    if (role) {
-      tags[`vertexai.request.contents.${contentIdx}.role`] = role
-    }
-
-    for (const [partIdx, part] of parts.entries()) {
-      this.tagRequestPart(part, tags, partIdx, contentIdx)
-    }
-  }
-
-  /**
-   * Generate the response tags.
-   *
-   * @param {Object} response
-   * @param {Span} span
-   * @returns {Object}
-   */
-  tagResponse (response, span) {
-    const tags = {}
-    const isSampled = this.isPromptCompletionSampled(span)
-
-    const candidates = response.candidates
-    for (const [candidateIdx, candidate] of candidates.entries()) {
-      const finishReason = candidate.finishReason
-      if (finishReason) {
-        tags[`vertexai.response.candidates.${candidateIdx}.finish_reason`] = finishReason
-      }
-      const candidateContent = candidate.content
-      const role = candidateContent.role
-      tags[`vertexai.response.candidates.${candidateIdx}.content.role`] = role
-
-      if (!isSampled) continue
-
-      const parts = candidateContent.parts
-      for (const [partIdx, part] of parts.entries()) {
-        const text = part.text
-        tags[`vertexai.response.candidates.${candidateIdx}.content.parts.${partIdx}.text`] =
-          this.normalize(String(text))
-
-        const functionCall = part.functionCall
-        if (!functionCall) continue
-
-        tags[`vertexai.response.candidates.${candidateIdx}.content.parts.${partIdx}.function_call.name`] =
-          functionCall.name
-        tags[`vertexai.response.candidates.${candidateIdx}.content.parts.${partIdx}.function_call.args`] =
-          this.normalize(JSON.stringify(functionCall.args))
-      }
-    }
-
-    const tokenCounts = response.usageMetadata
-    if (tokenCounts) {
-      tags['vertexai.response.usage.prompt_tokens'] = tokenCounts.promptTokenCount
-      tags['vertexai.response.usage.completion_tokens'] = tokenCounts.candidatesTokenCount
-      tags['vertexai.response.usage.total_tokens'] = tokenCounts.totalTokenCount
-    }
-
     return tags
   }
 }
diff --git a/packages/datadog-plugin-google-cloud-vertexai/test/index.spec.js b/packages/datadog-plugin-google-cloud-vertexai/test/index.spec.js
index 22d0a76affa..b28d32b126d 100644
--- a/packages/datadog-plugin-google-cloud-vertexai/test/index.spec.js
+++ b/packages/datadog-plugin-google-cloud-vertexai/test/index.spec.js
@@ -100,29 +100,11 @@ describe('Plugin', () => {
             expect(span.meta).to.have.property('span.kind', 'client')
 
             expect(span.meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
-            expect(span.meta).to.have.property('vertexai.request.contents.0.role', 'user')
-            expect(span.meta).to.have.property('vertexai.request.contents.0.parts.0.text', 'Hello, how are you?')
-            expect(span.meta).to.have.property('vertexai.response.candidates.0.finish_reason', 'STOP')
-            expect(span.meta).to.have.property('vertexai.response.candidates.0.content.parts.0.text',
-              'Hello! How can I assist you today?')
-            expect(span.meta).to.have.property('vertexai.response.candidates.0.content.role', 'model')
-
-            expect(span.metrics).to.have.property('vertexai.response.usage.prompt_tokens', 35)
-            expect(span.metrics).to.have.property('vertexai.response.usage.completion_tokens', 2)
-            expect(span.metrics).to.have.property('vertexai.response.usage.total_tokens', 37)
-
-            if (model.systemInstruction) {
-              expect(span.meta).to.have.property('vertexai.request.system_instruction.0.text',
-                'Please provide an answer')
-            }
-            expect(span.meta).to.have.property('vertexai.request.generation_config.max_output_tokens', '50')
-            expect(span.meta).to.have.property('vertexai.request.generation_config.temperature', '1')
           })
 
           const { response } = await model.generateContent({
             contents: [{ role: 'user', parts: [{ text: 'Hello, how are you?' }] }]
           })
-
           expect(response).to.have.property('candidates')
 
           await checkTraces
@@ -130,8 +112,7 @@ describe('Plugin', () => {
 
         it('makes a successful call with a string argument', async () => {
           const checkTraces = agent.assertSomeTraces(traces => {
-            expect(traces[0][0].meta).to.have.property('vertexai.request.contents.0.text',
-              'Hello, how are you?')
+            expect(traces[0][0].meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
           })
 
           const { response } = await model.generateContent('Hello, how are you?')
@@ -148,11 +129,7 @@ describe('Plugin', () => {
             const checkTraces = agent.assertSomeTraces(traces => {
               const span = traces[0][0]
 
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.content.parts.0.text', 'undefined')
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.content.parts.0.function_call.name',
-                'add')
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.content.parts.0.function_call.args',
-                JSON.stringify({ a: 2, b: 2 }))
+              expect(span.meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
             })
 
             await model.generateContent('what is 2 + 2?')
@@ -174,24 +151,6 @@ describe('Plugin', () => {
             expect(span.meta).to.have.property('span.kind', 'client')
 
             expect(span.meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
-            expect(span.meta).to.have.property('vertexai.request.contents.0.text', 'Hello, how are you?')
-            expect(span.meta).to.have.property('vertexai.response.candidates.0.finish_reason', 'STOP')
-            expect(span.meta).to.have.property('vertexai.response.candidates.0.content.parts.0.text',
-              'Hi, how are you doing today my friend?')
-            expect(span.meta).to.have.property('vertexai.response.candidates.0.content.role', 'model')
-
-            expect(span.metrics).to.have.property('vertexai.response.usage.prompt_tokens', 5)
-            expect(span.metrics).to.have.property('vertexai.response.usage.completion_tokens', 10)
-            expect(span.metrics).to.have.property('vertexai.response.usage.total_tokens', 15)
-
-            if (model.systemInstruction) {
-              expect(span.meta).to.have.property('vertexai.request.system_instruction.0.text',
-                'Please provide an answer')
-            }
-            expect(span.meta).to.have.property('vertexai.request.generation_config.max_output_tokens', '50')
-            expect(span.meta).to.have.property('vertexai.request.generation_config.temperature', '1')
-
-            expect(span.metrics).to.have.property('vertexai.request.stream', 1)
           })
 
           const { stream, response } = await model.generateContentStream('Hello, how are you?')
@@ -226,28 +185,6 @@ describe('Plugin', () => {
               expect(span.meta).to.have.property('span.kind', 'client')
 
               expect(span.meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
-
-              expect(span.meta).to.have.property('vertexai.request.contents.0.role', 'user')
-              expect(span.meta).to.have.property('vertexai.request.contents.0.parts.0.text', 'Foobar?')
-              expect(span.meta).to.have.property('vertexai.request.contents.1.role', 'model')
-              expect(span.meta).to.have.property('vertexai.request.contents.1.parts.0.text', 'Foobar!')
-              expect(span.meta).to.have.property('vertexai.request.contents.2.parts.0.text', 'Hello, how are you?')
-
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.finish_reason', 'STOP')
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.content.parts.0.text',
-                'Hello! How can I assist you today?')
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.content.role', 'model')
-
-              expect(span.metrics).to.have.property('vertexai.response.usage.prompt_tokens', 35)
-              expect(span.metrics).to.have.property('vertexai.response.usage.completion_tokens', 2)
-              expect(span.metrics).to.have.property('vertexai.response.usage.total_tokens', 37)
-
-              if (model.systemInstruction) {
-                expect(span.meta).to.have.property('vertexai.request.system_instruction.0.text',
-                  'Please provide an answer')
-              }
-              expect(span.meta).to.have.property('vertexai.request.generation_config.max_output_tokens', '50')
-              expect(span.meta).to.have.property('vertexai.request.generation_config.temperature', '1')
             })
 
             const chat = model.startChat({
@@ -265,8 +202,7 @@ describe('Plugin', () => {
 
           it('tags a string input', async () => {
             const checkTraces = agent.assertSomeTraces(traces => {
-              expect(traces[0][0].meta).to.have.property('vertexai.request.contents.0.text',
-                'Hello, how are you?')
+              expect(traces[0][0].meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
             })
 
             const chat = model.startChat({})
@@ -279,10 +215,7 @@ describe('Plugin', () => {
 
           it('tags an array of string inputs', async () => {
             const checkTraces = agent.assertSomeTraces(traces => {
-              expect(traces[0][0].meta).to.have.property('vertexai.request.contents.0.text',
-                'Hello, how are you?')
-              expect(traces[0][0].meta).to.have.property('vertexai.request.contents.1.text',
-                'What should I do today?')
+              expect(traces[0][0].meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
             })
 
             const chat = model.startChat({})
@@ -306,24 +239,6 @@ describe('Plugin', () => {
               expect(span.meta).to.have.property('span.kind', 'client')
 
               expect(span.meta).to.have.property('vertexai.request.model', 'gemini-1.5-flash-002')
-              expect(span.meta).to.have.property('vertexai.request.contents.0.text', 'Hello, how are you?')
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.finish_reason', 'STOP')
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.content.parts.0.text',
-                'Hi, how are you doing today my friend?')
-              expect(span.meta).to.have.property('vertexai.response.candidates.0.content.role', 'model')
-
-              expect(span.metrics).to.have.property('vertexai.response.usage.prompt_tokens', 5)
-              expect(span.metrics).to.have.property('vertexai.response.usage.completion_tokens', 10)
-              expect(span.metrics).to.have.property('vertexai.response.usage.total_tokens', 15)
-
-              if (model.systemInstruction) {
-                expect(span.meta).to.have.property('vertexai.request.system_instruction.0.text',
-                  'Please provide an answer')
-              }
-              expect(span.meta).to.have.property('vertexai.request.generation_config.max_output_tokens', '50')
-              expect(span.meta).to.have.property('vertexai.request.generation_config.temperature', '1')
-
-              expect(span.metrics).to.have.property('vertexai.request.stream', 1)
             })
 
             const chat = model.startChat({})