diff --git a/apps/docs/content/docs/workflows/blocks/agent.mdx b/apps/docs/content/docs/workflows/blocks/agent.mdx
index b09e868ea93..c7a98cd9863 100644
--- a/apps/docs/content/docs/workflows/blocks/agent.mdx
+++ b/apps/docs/content/docs/workflows/blocks/agent.mdx
@@ -168,7 +168,7 @@ Live tool-call chips stream for **OpenAI, Anthropic, Azure Anthropic, Google, Ve
 | Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `claude-fable-5-1`, `claude-fable-5`, `claude-sonnet-5-5`, `claude-sonnet-5`, `claude-opus-5-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-5-5`, `claude-haiku-4-5` |
 | Azure OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `azure/gpt-6.1-sol`, `azure/gpt-6-sol`, `azure/gpt-6-luna`, `azure/gpt-6-astra`, `azure/gpt-5.6-sol`, `azure/gpt-5.6-terra`, `azure/gpt-5.6-luna`, `azure/gpt-5.5`, `azure/gpt-5.4-pro`, `azure/gpt-5.4`, `azure/gpt-5.4-mini`, `azure/gpt-5.4-nano`, `azure/gpt-5.2`, `azure/gpt-5.1`, `azure/gpt-5.1-codex`, `azure/gpt-5`, `azure/gpt-5-mini`, `azure/gpt-5-nano`, `azure/o3`, `azure/o4-mini` |
 | Azure Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `azure-anthropic/claude-fable-5-1`, `azure-anthropic/claude-opus-5-5`, `azure-anthropic/claude-sonnet-5-5`, `azure-anthropic/claude-haiku-5-5`, `azure-anthropic/claude-opus-5`, `azure-anthropic/claude-opus-4-8`, `azure-anthropic/claude-opus-4-7`, `azure-anthropic/claude-opus-4-6`, `azure-anthropic/claude-opus-4-5`, `azure-anthropic/claude-sonnet-5`, `azure-anthropic/claude-sonnet-4-6`, `azure-anthropic/claude-sonnet-4-5`, `azure-anthropic/claude-opus-4-1`, `azure-anthropic/claude-haiku-4-5` |
-| Google | Summaries only | `gemini-3.8-flash`, `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash-lite`, `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite` |
+| Google | Summaries only | `gemini-4-argon`, `gemini-3.8-flash`, `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash-lite`, `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite` |
 | Vertex AI | Summaries only | `vertex/gemini-3.8-flash`, `vertex/gemini-3.7-flash`, `vertex/gemini-3.6-flash`, `vertex/gemini-3.5-flash-lite`, `vertex/gemini-3.5-flash`, `vertex/gemini-3.1-pro-preview`, `vertex/gemini-3.1-flash-lite`, `vertex/gemini-3-flash-preview`, `vertex/gemini-2.5-pro`, `vertex/gemini-2.5-flash`, `vertex/gemini-2.5-flash-lite` |
 | DeepSeek | Full thinking deltas | `deepseek-v4-pro`, `deepseek-flash`, `deepseek-v4-flash`, `deepseek-reasoner` |
 | xAI | Full thinking deltas | `grok-4.6`, `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-0309` |
diff --git a/apps/sim/lib/knowledge/documents/image-extraction-gemini.ts b/apps/sim/lib/knowledge/documents/image-extraction-gemini.ts
index 135bfbec093..0252b7f7e5e 100644
--- a/apps/sim/lib/knowledge/documents/image-extraction-gemini.ts
+++ b/apps/sim/lib/knowledge/documents/image-extraction-gemini.ts
@@ -9,7 +9,7 @@ import { resolveProviderKey } from '@/lib/embeddings/keys'
 import { PermanentDocumentProcessingError } from '@/lib/knowledge/documents/document-processing-error'
 import { readBoundedHttpErrorPayload } from '@/lib/knowledge/documents/utils'
 import { getProviderModels } from '@/providers/models'
-import { isGemini3Model } from '@/providers/utils'
+import { isGemini3OrLaterModel } from '@/providers/utils'
 
 const logger = createLogger('GeminiImageExtraction')
 
@@ -22,7 +22,7 @@ export const DEFAULT_IMAGE_EXTRACTION_MODEL = 'gemini-3.8-flash'
 
 /**
  * Transcription needs little reasoning, and Gemini bills thinking as output that
- * also spends the output budget. Every Gemini 3 model accepts `LOW`.
+ * also spends the output budget. Gemini 3 and later models accept `LOW`.
  */
 const THINKING_LEVEL = 'LOW'
 
@@ -72,19 +72,19 @@ export class GeminiImageExtractionError extends Error {
 
 /**
  * The model from `KB_IMAGE_EXTRACTION_MODEL`, or the default when it is unset or
- * not a Gemini 3 model in the catalog: the request uses Gemini 3's JSON-schema
- * output and thinking level, and only catalog models carry the pricing that
+ * not a Gemini 3 or later model in the catalog: the request uses modern Gemini
+ * JSON-schema output and thinking level, and only catalog models carry the pricing that
  * bills each image. Never throws: a bad value must not stop indexing.
  */
 export function resolveImageExtractionModel(): string {
   const configured = env.KB_IMAGE_EXTRACTION_MODEL?.trim()
   if (!configured) return DEFAULT_IMAGE_EXTRACTION_MODEL
   const catalogModel = getProviderModels('google').find(
-    (id) => id.toLowerCase() === configured.toLowerCase() && isGemini3Model(id)
+    (id) => id.toLowerCase() === configured.toLowerCase() && isGemini3OrLaterModel(id)
   )
   if (catalogModel) return catalogModel
   logger.warn(
-    `KB_IMAGE_EXTRACTION_MODEL="${configured}" is not a supported Gemini 3 model, falling back to ${DEFAULT_IMAGE_EXTRACTION_MODEL}`
+    `KB_IMAGE_EXTRACTION_MODEL="${configured}" is not a supported Gemini 3 or later model, falling back to ${DEFAULT_IMAGE_EXTRACTION_MODEL}`
   )
   return DEFAULT_IMAGE_EXTRACTION_MODEL
 }
diff --git a/apps/sim/providers/gemini/config.ts b/apps/sim/providers/gemini/config.ts
new file mode 100644
index 00000000000..32576759f9f
--- /dev/null
+++ b/apps/sim/providers/gemini/config.ts
@@ -0,0 +1,29 @@
+import { FunctionCallingConfigMode, type GenerateContentConfig, type Schema } from '@google/genai'
+import { cleanSchemaForGemini } from '@/providers/google/utils'
+import type { ProviderRequest } from '@/providers/types'
+import { isGemini3OrLaterModel } from '@/providers/utils'
+
+/** Applies the response schema only on turns that can accept it alongside their tool configuration. */
+export function applyGeminiResponseFormat(
+  config: GenerateContentConfig,
+  responseFormat: ProviderRequest['responseFormat'],
+  model: string
+): void {
+  if (!responseFormat) return
+
+  if (config.toolConfig?.functionCallingConfig?.mode === FunctionCallingConfigMode.ANY) {
+    config.responseMimeType = undefined
+    config.responseSchema = undefined
+    config.responseJsonSchema = undefined
+    return
+  }
+
+  if (config.tools?.length && !isGemini3OrLaterModel(model)) return
+
+  config.responseMimeType = 'application/json'
+  if (isGemini3OrLaterModel(model)) {
+    config.responseJsonSchema = responseFormat.schema
+  } else {
+    config.responseSchema = cleanSchemaForGemini(responseFormat.schema) as Schema
+  }
+}
diff --git a/apps/sim/providers/gemini/core.test.ts b/apps/sim/providers/gemini/core.test.ts
index 9e0ce6a8d77..bb69686778f 100644
--- a/apps/sim/providers/gemini/core.test.ts
+++ b/apps/sim/providers/gemini/core.test.ts
@@ -118,6 +118,7 @@ describe('Vertex Gemini request compatibility', () => {
   })
 
   it.each([
+    'gemini-4-argon',
     'vertex/gemini-3.8-flash',
     'vertex/gemini-3.7-flash',
     'vertex/gemini-3.6-flash',
diff --git a/apps/sim/providers/gemini/core.ts b/apps/sim/providers/gemini/core.ts
index 17970aa8aaa..94c10af2102 100644
--- a/apps/sim/providers/gemini/core.ts
+++ b/apps/sim/providers/gemini/core.ts
@@ -7,7 +7,6 @@ import {
   type GoogleGenAI,
   type Interactions,
   type Part,
-  type Schema,
   type ThinkingConfig,
   type ToolConfig,
 } from '@google/genai'
@@ -21,11 +20,11 @@ import {
   captureProviderConversationStep,
   recordProviderConversationToolError,
 } from '@/providers/conversation-history'
+import { applyGeminiResponseFormat } from '@/providers/gemini/config'
 import { createGeminiStreamingToolLoopStream } from '@/providers/gemini/streaming-tool-loop'
 import { priceGeminiTokens, splitGeminiTokens, splitGeminiUsage } from '@/providers/gemini/usage'
 import {
   checkForForcedToolUsage,
-  cleanSchemaForGemini,
   convertToGeminiFormat,
   convertUsageMetadata,
   createReadableStreamFromGeminiStream,
@@ -53,7 +52,7 @@ import type {
 } from '@/providers/types'
 import {
   isDeepResearchModel,
-  isGemini3Model,
+  isGemini3OrLaterModel,
   prepareToolExecution,
   prepareToolsWithUsageControl,
   sumToolCosts,
@@ -362,19 +361,14 @@ function buildNextConfig(
   if (allForcedToolsUsed && request.responseFormat) {
     nextConfig.tools = undefined
     nextConfig.toolConfig = undefined
-    if (isGemini3Model(model)) {
-      logger.info('Gemini 3: Stripping tools after forced tool execution, schema already set')
-    } else {
-      nextConfig.responseMimeType = 'application/json'
-      nextConfig.responseSchema = cleanSchemaForGemini(request.responseFormat.schema) as Schema
-      logger.info('Using structured output for final response after tool execution')
-    }
+    logger.info('Using structured output for final response after tool execution')
   } else if (state.currentToolConfig) {
     nextConfig.toolConfig = state.currentToolConfig
   } else {
     nextConfig.toolConfig = { functionCallingConfig: { mode: FunctionCallingConfigMode.AUTO } }
   }
 
+  applyGeminiResponseFormat(nextConfig, request.responseFormat, model)
   return nextConfig
 }
 
@@ -1006,27 +1000,12 @@ export async function executeGeminiRequest(
       geminiConfig.systemInstruction = systemInstruction
     }
 
-    // Handle response format
-    if (request.responseFormat && !tools?.length) {
-      geminiConfig.responseMimeType = 'application/json'
-      geminiConfig.responseSchema = cleanSchemaForGemini(request.responseFormat.schema) as Schema
-      logger.info('Using Gemini native structured output format')
-    } else if (request.responseFormat && tools?.length && isGemini3Model(model)) {
-      geminiConfig.responseMimeType = 'application/json'
-      geminiConfig.responseJsonSchema = request.responseFormat.schema
-      logger.info('Using Gemini 3 structured output with tools (responseJsonSchema)')
-    } else if (request.responseFormat && tools?.length) {
-      logger.warn(
-        'Gemini 2 does not support responseFormat with tools. Structured output will be applied after tool execution.'
-      )
-    }
-
-    // Gemini 3.x takes thinkingLevel directly; Gemini 2.5-series rejects it and needs thinkingBudget.
+    // Gemini 3 and later take thinkingLevel directly; Gemini 2.5-series rejects it and needs thinkingBudget.
     // includeThoughts is required for thought parts to appear; it is requested
     // only on agent-events runs so legacy runs keep the pre-agent-events payload.
     if (request.thinkingLevel && request.thinkingLevel !== 'none') {
       const thinkingConfig: ThinkingConfig = { includeThoughts: request.agentEvents === true }
-      if (isGemini3Model(model)) {
+      if (isGemini3OrLaterModel(model)) {
         thinkingConfig.thinkingLevel = mapToThinkingLevel(request.thinkingLevel)
       } else {
         thinkingConfig.thinkingBudget = mapToThinkingBudget(model, request.thinkingLevel)
@@ -1034,7 +1013,7 @@ export async function executeGeminiRequest(
       geminiConfig.thinkingConfig = thinkingConfig
     } else if (
       request.thinkingLevel === 'none' &&
-      !isGemini3Model(model) &&
+      !isGemini3OrLaterModel(model) &&
       supportsDisablingGemini25Thinking(model)
     ) {
       // Omitting thinkingConfig falls back to the API's dynamic default (ON for gemini-2.5-flash),
@@ -1087,17 +1066,19 @@ export async function executeGeminiRequest(
       }
     }
 
+    applyGeminiResponseFormat(geminiConfig, request.responseFormat, model)
+
     const initialCallTime = Date.now()
     /**
      * Gemini 2 cannot combine responseSchema with tools, so structured output
      * is applied on a final schema-configured request after tools settle — the
      * silent path does this; the live loop would break as soon as a turn has
-     * no calls and skip the schema. Gemini 3 carries responseJsonSchema
-     * alongside tools, so its live loop keeps structured output.
+     * no calls and skip the schema. Gemini 3 and later carry responseJsonSchema
+     * alongside automatic tools, or apply it after forced calls settle.
      */
     const hasActiveTools = Boolean(geminiConfig.tools?.length)
     const responseFormatNeedsFinalPass =
-      Boolean(request.responseFormat) && hasActiveTools && !isGemini3Model(model)
+      Boolean(request.responseFormat) && hasActiveTools && !isGemini3OrLaterModel(model)
     const liveToolLoopSupported = !responseFormatNeedsFinalPass
     const shouldStream = request.stream && !hasActiveTools
 
@@ -1262,10 +1243,7 @@ export async function executeGeminiRequest(
         tools: undefined,
         toolConfig: undefined,
       }
-      if (request.responseFormat && !isGemini3Model(model)) {
-        finalConfig.responseMimeType = 'application/json'
-        finalConfig.responseSchema = cleanSchemaForGemini(request.responseFormat.schema) as Schema
-      }
+      applyGeminiResponseFormat(finalConfig, request.responseFormat, model)
 
       const finalStartTime = Date.now()
       const finalResponsePayload = await prepareConversationGeneration(request, 'gemini', {
diff --git a/apps/sim/providers/gemini/streaming-tool-loop.ts b/apps/sim/providers/gemini/streaming-tool-loop.ts
index c57bce99fde..223d0b93a8b 100644
--- a/apps/sim/providers/gemini/streaming-tool-loop.ts
+++ b/apps/sim/providers/gemini/streaming-tool-loop.ts
@@ -20,7 +20,6 @@ import {
   type GenerateContentResponse,
   type GoogleGenAI,
   type Part,
-  type Schema,
   type ToolConfig,
 } from '@google/genai'
 import type { Logger } from '@sim/logger'
@@ -32,9 +31,9 @@ import {
   captureProviderConversationStep,
   recordProviderConversationToolError,
 } from '@/providers/conversation-history'
+import { applyGeminiResponseFormat } from '@/providers/gemini/config'
 import {
   checkForForcedToolUsage,
-  cleanSchemaForGemini,
   convertUsageMetadata,
   ensureStructResponse,
   geminiRetryDelayMs,
@@ -51,7 +50,7 @@ import {
 import { ensureToolCallId } from '@/providers/tool-call-id'
 import { enrichLastModelSegment } from '@/providers/trace-enrichment'
 import type { ModelPricing, ProviderRequest, TimeSegment } from '@/providers/types'
-import { isGemini3Model, prepareToolExecution, sumToolCosts } from '@/providers/utils'
+import { prepareToolExecution, sumToolCosts } from '@/providers/utils'
 import type { GeminiUsage } from './types'
 import { priceGeminiTokens, splitGeminiUsage } from './usage'
 
@@ -96,19 +95,14 @@ function buildNextConfig(
   if (allForcedToolsUsed && request.responseFormat) {
     nextConfig.tools = undefined
     nextConfig.toolConfig = undefined
-    if (isGemini3Model(model)) {
-      logger.info('Gemini 3: Stripping tools after forced tool execution, schema already set')
-    } else {
-      nextConfig.responseMimeType = 'application/json'
-      nextConfig.responseSchema = cleanSchemaForGemini(request.responseFormat.schema) as Schema
-      logger.info('Using structured output for final response after tool execution')
-    }
+    logger.info('Using structured output for final response after tool execution')
   } else if (currentToolConfig) {
     nextConfig.toolConfig = currentToolConfig
   } else {
     nextConfig.toolConfig = { functionCallingConfig: { mode: FunctionCallingConfigMode.AUTO } }
   }
 
+  applyGeminiResponseFormat(nextConfig, request.responseFormat, model)
   return nextConfig
 }
 
@@ -310,6 +304,8 @@ export function createGeminiStreamingToolLoopStream(
                   model
                 )
 
+            applyGeminiResponseFormat(turnConfig, request.responseFormat, model)
+
             const modelStart = Date.now()
             const turnPayload = await prepareConversationGeneration(request, 'gemini', {
               model,
diff --git a/apps/sim/providers/google/index.live.test.ts b/apps/sim/providers/google/index.live.test.ts
new file mode 100644
index 00000000000..3c3f17b8245
--- /dev/null
+++ b/apps/sim/providers/google/index.live.test.ts
@@ -0,0 +1,189 @@
+import { writeFile } from 'node:fs/promises'
+import { getErrorMessage } from '@sim/utils/errors'
+import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest'
+import type { StreamingExecution } from '@/executor/types'
+import { executeProviderRequest } from '@/providers'
+import type { ProviderRequest, ProviderResponse } from '@/providers/types'
+
+vi.unmock('@/tools/registry')
+vi.unmock('@/tools/metadata')
+vi.unmock('@/tools/metadata-outputs')
+
+const model = process.env.GEMINI_LIVE_MODEL || 'gemini-4-argon'
+const apiKey = process.env.GEMINI_API_KEY
+const reportPath = process.env.GEMINI_REPORT_PATH
+const results: Array<{
+  name: string
+  status: 'passed' | 'failed'
+  durationMs: number
+  error?: string
+}> = []
+
+async function check(name: string, run: () => Promise<void>) {
+  const start = Date.now()
+  try {
+    await run()
+    results.push({ name, status: 'passed', durationMs: Date.now() - start })
+  } catch (error) {
+    results.push({
+      name,
+      status: 'failed',
+      durationMs: Date.now() - start,
+      error: getErrorMessage(error),
+    })
+    throw error
+  }
+}
+
+async function execute(request: Partial<ProviderRequest> = {}) {
+  expect(vi.isMockFunction(globalThis.fetch)).toBe(false)
+  return executeProviderRequest('google', {
+    model,
+    apiKey,
+    maxTokens: 65536,
+    thinkingLevel: 'low',
+    abortSignal: AbortSignal.timeout(120_000),
+    messages: [{ role: 'user', content: 'Reply with only the result of 6 times 7.' }],
+    ...request,
+  })
+}
+
+beforeAll(() => {
+  if (!apiKey) throw new Error('Set GEMINI_API_KEY to a Gemini API key with model access')
+  if (!reportPath) throw new Error('Set GEMINI_REPORT_PATH to a writable JSON report path')
+})
+
+afterAll(async () => {
+  if (reportPath) {
+    await writeFile(
+      reportPath,
+      JSON.stringify({ model, recordedAt: new Date().toISOString(), results }, null, 2)
+    )
+  }
+})
+
+describe('Google Gemini live acceptance', () => {
+  it.each(['low', 'medium', 'high'])(
+    'answers with %s thinking',
+    async (thinkingLevel) => {
+      await check(`thinking:${thinkingLevel}`, async () => {
+        const result = (await execute({ thinkingLevel })) as ProviderResponse
+        expect(result.content.trim()).toBe('42')
+        expect(result.tokens?.total).toBeGreaterThan(0)
+        expect(result.cost?.total).toBeGreaterThan(0)
+      })
+    },
+    120_000
+  )
+
+  it('returns a native JSON-schema answer', async () => {
+    await check('structured-output', async () => {
+      const result = (await execute({
+        responseFormat: {
+          name: 'answer',
+          schema: {
+            type: 'object',
+            properties: { answer: { type: 'integer' } },
+            required: ['answer'],
+            additionalProperties: false,
+          },
+        },
+      })) as ProviderResponse
+      expect(JSON.parse(result.content)).toEqual({ answer: 42 })
+    })
+  }, 120_000)
+
+  it('reads an inline image through the attachment pipeline', async () => {
+    await check('vision', async () => {
+      const base64 =
+        'iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAIAAAAlC+aJAAAAb0lEQVR4nO3PAQkAAAyEwO9feoshgnABdLep8QUNyPEFDcjxBQ3I8QUNyPEFDcjxBQ3I8QUNyPEFDcjxBQ3I8QUNyPEFDcjxBQ3I8QUNyPEFDcjxBQ3I8QUNyPEFDcjxBQ3I8QUNyPEFDcjxBQ3I8QUNyPEFDcjxBQ3IPanc8OLDQitxAAAAAElFTkSuQmCC'
+      const result = (await execute({
+        messages: [
+          {
+            role: 'user',
+            content: 'What is the dominant color in this image? Reply with one color word.',
+            files: [
+              {
+                id: 'inline-fixture',
+                name: 'fixture.png',
+                url: '',
+                key: '',
+                type: 'image/png',
+                size: Buffer.from(base64, 'base64').length,
+                base64,
+              },
+            ],
+          },
+        ],
+      })) as ProviderResponse
+      expect(result.content.toLowerCase()).toContain('red')
+      expect(result.tokens?.total).toBeGreaterThan(0)
+    })
+  }, 120_000)
+
+  it('streams answer events and settles usage', async () => {
+    await check('stream', async () => {
+      const result = (await execute({ stream: true, agentEvents: true })) as StreamingExecution
+      const reader = result.stream.getReader()
+      while (!(await reader.read()).done) {}
+      const execution = await result.execution
+      expect(execution.output.content?.trim()).toBe('42')
+      expect(execution.output.tokens?.total).toBeGreaterThan(0)
+      expect(execution.output.cost?.total).toBeGreaterThan(0)
+    })
+  }, 120_000)
+
+  it.each([false, true])(
+    'returns structured output after a real HTTP tool (stream=%s)',
+    async (stream) => {
+      await check(`structured-tool-loop:stream=${stream}`, async () => {
+        const result = await execute({
+          stream,
+          agentEvents: stream,
+          messages: [
+            {
+              role: 'user',
+              content:
+                'Fetch https://example.com with the tool, then return its HTTP status as status.',
+            },
+          ],
+          tools: [
+            {
+              id: 'http_request',
+              description: 'Fetch the example page',
+              usageControl: 'force',
+              params: { url: 'https://example.com', method: 'GET' },
+              parameters: { type: 'object', properties: {}, required: [] },
+            },
+          ],
+          responseFormat: {
+            name: 'status',
+            schema: {
+              type: 'object',
+              properties: { status: { type: 'integer' } },
+              required: ['status'],
+              additionalProperties: false,
+            },
+          },
+        })
+        if (stream) {
+          const streaming = result as StreamingExecution
+          const reader = streaming.stream.getReader()
+          while (!(await reader.read()).done) {}
+          const execution = await streaming.execution
+          expect(JSON.parse(execution.output.content ?? '')).toEqual({ status: 200 })
+          expect(
+            execution.output.toolCalls?.list.find((call) => call.name === 'http_request')?.result
+          ).toMatchObject({ status: 200 })
+        } else {
+          const response = result as ProviderResponse
+          expect(JSON.parse(response.content)).toEqual({ status: 200 })
+          expect(
+            response.toolCalls?.find((call) => call.name === 'http_request')?.result
+          ).toMatchObject({ status: 200 })
+        }
+      })
+    },
+    120_000
+  )
+})
diff --git a/apps/sim/providers/models.ts b/apps/sim/providers/models.ts
index e384a3848e8..ac769c5421c 100644
--- a/apps/sim/providers/models.ts
+++ b/apps/sim/providers/models.ts
@@ -2496,6 +2496,25 @@ export const PROVIDER_DEFINITIONS: Record<string, ProviderDefinition> = {
     icon: GeminiIcon,
     color: '#4285F4',
     models: [
+      {
+        id: 'gemini-4-argon',
+        pricing: {
+          input: 2,
+          cachedInput: 0.1,
+          output: 10,
+          updatedAt: '2026-10-13',
+        },
+        capabilities: {
+          thinking: {
+            levels: ['low', 'medium', 'high'],
+            default: 'medium',
+          },
+          maxOutputTokens: 65536,
+        },
+        contextWindow: 1048576,
+        releaseDate: '2026-09-30',
+        recommended: true,
+      },
       {
         id: 'gemini-3.8-flash',
         pricing: {
diff --git a/apps/sim/providers/utils.test.ts b/apps/sim/providers/utils.test.ts
index 304e4f05661..14e238e93a1 100644
--- a/apps/sim/providers/utils.test.ts
+++ b/apps/sim/providers/utils.test.ts
@@ -35,7 +35,7 @@ import {
   getBaseModelProviders,
   getProvider,
   getProviderFromModel,
-  isGemini3Model,
+  isGemini3OrLaterModel,
   prepareToolExecution,
   prepareToolsWithUsageControl,
   shouldBillModelUsage,
@@ -1540,7 +1540,7 @@ describe('findProviderFromModel', () => {
   })
 })
 
-describe('isGemini3Model', () => {
+describe('isGemini3OrLaterModel', () => {
   it.each([
     'gemini-3.8-flash',
     'VERTEX/gemini-3.8-flash',
@@ -1548,15 +1548,15 @@ describe('isGemini3Model', () => {
     'vertex/publishers/google/models/gemini-3.8-flash',
     'vertex/projects/test-project/locations/global/publishers/google/models/gemini-3.8-flash',
   ])('recognizes the Gemini family in %s', (model) => {
-    expect(isGemini3Model(model)).toBe(true)
+    expect(isGemini3OrLaterModel(model)).toBe(true)
   })
 
   it.each([
     'vertex/gemini-2.5-pro',
     'vertex/custom-gemini-3-deployment',
     'vertex/publishers/another-provider/models/gemini-3.8-flash',
-  ])('does not infer Gemini 3 behavior from %s', (model) => {
-    expect(isGemini3Model(model)).toBe(false)
+  ])('does not infer modern Gemini behavior from %s', (model) => {
+    expect(isGemini3OrLaterModel(model)).toBe(false)
   })
 })
 
diff --git a/apps/sim/providers/utils.ts b/apps/sim/providers/utils.ts
index 1cc8a03d458..cc02cf7bbfd 100644
--- a/apps/sim/providers/utils.ts
+++ b/apps/sim/providers/utils.ts
@@ -1491,7 +1491,8 @@ export function isDeepResearchModel(model: string): boolean {
   return MODELS_WITH_DEEP_RESEARCH.includes(model.toLowerCase())
 }
 
-export function isGemini3Model(model: string): boolean {
+/** Accepts bare Gemini IDs, google/ or vertex/ prefixes, and Google publisher resource names. */
+export function isGemini3OrLaterModel(model: string): boolean {
   const normalized = model
     .toLowerCase()
     .replace(/^vertex\//, '')
@@ -1499,7 +1500,7 @@ export function isGemini3Model(model: string): boolean {
       /^(?:google\/|(?:projects\/[^/]+\/locations\/[^/]+\/)?publishers\/google\/models\/)/,
       ''
     )
-  return normalized.startsWith('gemini-3')
+  return Number(normalized.match(/^gemini-(\d+)(?:[.-]|$)/)?.[1]) >= 3
 }
 
 /**
diff --git a/apps/sim/providers/vertex/index.ts b/apps/sim/providers/vertex/index.ts
index 65e49151d81..ea5edba6328 100644
--- a/apps/sim/providers/vertex/index.ts
+++ b/apps/sim/providers/vertex/index.ts
@@ -10,7 +10,7 @@ import type { StreamingExecution } from '@/executor/types'
 import { executeGeminiRequest } from '@/providers/gemini/core'
 import { getProviderDefaultModel, getProviderModels } from '@/providers/models'
 import type { ProviderConfig, ProviderRequest, ProviderResponse } from '@/providers/types'
-import { isGemini3Model } from '@/providers/utils'
+import { isGemini3OrLaterModel } from '@/providers/utils'
 
 const logger = createLogger('VertexProvider')
 
@@ -37,11 +37,11 @@ export const vertexProvider: ProviderConfig = {
   ): Promise<ProviderResponse | StreamingExecution> => {
     const model = request.model.replace(/^vertex\//i, '')
     const vertexProject = request.vertexProject || env.VERTEX_PROJECT
-    /** Gemini 3 models use global or multi-region endpoints instead of legacy regions. */
+    /** Gemini 3 and later use global or multi-region endpoints instead of legacy regions. */
     const vertexLocation = (
       request.vertexLocation ||
       env.VERTEX_LOCATION ||
-      (isGemini3Model(model) ? 'global' : 'us-central1')
+      (isGemini3OrLaterModel(model) ? 'global' : 'us-central1')
     ).toLowerCase()
 
     if (!vertexProject) {
diff --git a/packages/testing/src/mocks/providers-utils.mock.ts b/packages/testing/src/mocks/providers-utils.mock.ts
index d0309338198..573fd6a9714 100644
--- a/packages/testing/src/mocks/providers-utils.mock.ts
+++ b/packages/testing/src/mocks/providers-utils.mock.ts
@@ -126,7 +126,7 @@ export const providersUtilsMockFns = {
   mockSupportsThinking: vi.fn((_model: string): boolean => false),
   mockSupportsPromptCaching: vi.fn((_model: string): boolean => false),
   mockIsDeepResearchModel: vi.fn((_model: string): boolean => false),
-  mockIsGemini3Model: vi.fn((_model: string): boolean => false),
+  mockIsGemini3OrLaterModel: vi.fn((_model: string): boolean => false),
   mockPrepareToolExecution: vi.fn(
     (
       _tool: unknown,
@@ -202,7 +202,7 @@ export const providersUtilsMock = {
   supportsThinking: providersUtilsMockFns.mockSupportsThinking,
   supportsPromptCaching: providersUtilsMockFns.mockSupportsPromptCaching,
   isDeepResearchModel: providersUtilsMockFns.mockIsDeepResearchModel,
-  isGemini3Model: providersUtilsMockFns.mockIsGemini3Model,
+  isGemini3OrLaterModel: providersUtilsMockFns.mockIsGemini3OrLaterModel,
   prepareToolExecution: providersUtilsMockFns.mockPrepareToolExecution,
   checkForForcedToolUsageOpenAI: providersUtilsMockFns.mockCheckForForcedToolUsageOpenAI,
 }