diff --git a/dev-packages/node-integration-tests/suites/tracing/vercelai/instrument-streaming-with-truncation.mjs b/dev-packages/node-integration-tests/suites/tracing/vercelai/instrument-streaming-with-truncation.mjs
new file mode 100644
index 000000000000..39c60d69dacb
--- /dev/null
+++ b/dev-packages/node-integration-tests/suites/tracing/vercelai/instrument-streaming-with-truncation.mjs
@@ -0,0 +1,16 @@
+import * as Sentry from '@sentry/node';
+import { loggingTransport } from '@sentry-internal/node-integration-tests';
+
+Sentry.init({
+  dsn: 'https://public@dsn.ingest.sentry.io/1337',
+  release: '1.0',
+  tracesSampleRate: 1.0,
+  sendDefaultPii: true,
+  transport: loggingTransport,
+  traceLifecycle: 'stream',
+  integrations: [
+    Sentry.vercelAIIntegration({
+      enableTruncation: true,
+    }),
+  ],
+});
diff --git a/dev-packages/node-integration-tests/suites/tracing/vercelai/instrument-streaming.mjs b/dev-packages/node-integration-tests/suites/tracing/vercelai/instrument-streaming.mjs
new file mode 100644
index 000000000000..48a860c510c5
--- /dev/null
+++ b/dev-packages/node-integration-tests/suites/tracing/vercelai/instrument-streaming.mjs
@@ -0,0 +1,11 @@
+import * as Sentry from '@sentry/node';
+import { loggingTransport } from '@sentry-internal/node-integration-tests';
+
+Sentry.init({
+  dsn: 'https://public@dsn.ingest.sentry.io/1337',
+  release: '1.0',
+  tracesSampleRate: 1.0,
+  sendDefaultPii: true,
+  transport: loggingTransport,
+  traceLifecycle: 'stream',
+});
diff --git a/dev-packages/node-integration-tests/suites/tracing/vercelai/scenario-streaming.mjs b/dev-packages/node-integration-tests/suites/tracing/vercelai/scenario-streaming.mjs
new file mode 100644
index 000000000000..7f824dee4a3e
--- /dev/null
+++ b/dev-packages/node-integration-tests/suites/tracing/vercelai/scenario-streaming.mjs
@@ -0,0 +1,30 @@
+import * as Sentry from '@sentry/node';
+import { generateText } from 'ai';
+import { MockLanguageModelV1 } from 'ai/test';
+
+async function run() {
+  await Sentry.startSpan({ op: 'function', name: 'main' }, async () => {
+    const longContent = 'A'.repeat(50_000);
+    await generateText({
+      experimental_telemetry: { isEnabled: true },
+      model: new MockLanguageModelV1({
+        doGenerate: async () => ({
+          rawCall: { rawPrompt: null, rawSettings: {} },
+          finishReason: 'stop',
+          usage: { promptTokens: 10, completionTokens: 5 },
+          text: 'Response',
+        }),
+      }),
+      messages: [
+        { role: 'user', content: longContent },
+        { role: 'assistant', content: 'Some reply' },
+        { role: 'user', content: 'Follow-up question' },
+      ],
+    });
+  });
+
+  // Flush is required when span streaming is enabled to ensure streamed spans are sent before the process exits
+  await Sentry.flush(2000);
+}
+
+run();
diff --git a/dev-packages/node-integration-tests/suites/tracing/vercelai/test.ts b/dev-packages/node-integration-tests/suites/tracing/vercelai/test.ts
index d75a1faf8ea0..df2632ad635b 100644
--- a/dev-packages/node-integration-tests/suites/tracing/vercelai/test.ts
+++ b/dev-packages/node-integration-tests/suites/tracing/vercelai/test.ts
@@ -983,4 +983,50 @@ describe('Vercel AI integration', () => {
       });
     },
   );
+
+  const streamingLongContent = 'A'.repeat(50_000);
+
+  createEsmAndCjsTests(__dirname, 'scenario-streaming.mjs', 'instrument-streaming.mjs', (createRunner, test) => {
+    test('automatically disables truncation when span streaming is enabled', async () => {
+      await createRunner()
+        .expect({
+          span: container => {
+            const spans = container.items;
+
+            const chatSpan = spans.find(s =>
+              s.attributes?.[GEN_AI_INPUT_MESSAGES_ATTRIBUTE]?.value?.includes(streamingLongContent),
+            );
+            expect(chatSpan).toBeDefined();
+          },
+        })
+        .start()
+        .completed();
+    });
+  });
+
+  createEsmAndCjsTests(
+    __dirname,
+    'scenario-streaming.mjs',
+    'instrument-streaming-with-truncation.mjs',
+    (createRunner, test) => {
+      test('respects explicit enableTruncation: true even when span streaming is enabled', async () => {
+        await createRunner()
+          .expect({
+            span: container => {
+              const spans = container.items;
+
+              // With explicit enableTruncation: true, truncation keeps only the last message
+              // and drops the long content. The result should NOT contain the full 50k 'A' string.
+              const chatSpan = spans.find(s =>
+                s.attributes?.[GEN_AI_INPUT_MESSAGES_ATTRIBUTE]?.value?.includes('Follow-up question'),
+              );
+              expect(chatSpan).toBeDefined();
+              expect(chatSpan!.attributes[GEN_AI_INPUT_MESSAGES_ATTRIBUTE].value).not.toContain(streamingLongContent);
+            },
+          })
+          .start()
+          .completed();
+      });
+    },
+  );
 });
diff --git a/packages/core/src/tracing/ai/utils.ts b/packages/core/src/tracing/ai/utils.ts
index d3cce644dbc1..05502b249efb 100644
--- a/packages/core/src/tracing/ai/utils.ts
+++ b/packages/core/src/tracing/ai/utils.ts
@@ -3,6 +3,7 @@
  */
 import { captureException } from '../../exports';
 import { getClient } from '../../currentScopes';
+import { hasSpanStreamingEnabled } from '../spans/hasSpanStreamingEnabled';
 import type { Span } from '../../types-hoist/span';
 import { isThenable } from '../../utils/is';
 import {
@@ -56,6 +57,16 @@ export function resolveAIRecordingOptions<T extends AIRecordingOptions>(options?
   } as T & Required<AIRecordingOptions>;
 }
 
+/**
+ * Resolves whether truncation should be enabled.
+ * If the user explicitly set `enableTruncation`, that value is used.
+ * Otherwise, truncation is disabled when span streaming is active.
+ */
+export function shouldEnableTruncation(enableTruncation: boolean | undefined): boolean {
+  const client = getClient();
+  return enableTruncation ?? !(client && hasSpanStreamingEnabled(client));
+}
+
 /**
  * Build method path from current traversal
  */
diff --git a/packages/core/src/tracing/vercel-ai/index.ts b/packages/core/src/tracing/vercel-ai/index.ts
index 90fb1b16fc65..569233cf8321 100644
--- a/packages/core/src/tracing/vercel-ai/index.ts
+++ b/packages/core/src/tracing/vercel-ai/index.ts
@@ -2,6 +2,7 @@
 import type { Client } from '../../client';
 import { getClient } from '../../currentScopes';
 import { SEMANTIC_ATTRIBUTE_SENTRY_OP, SEMANTIC_ATTRIBUTE_SENTRY_ORIGIN } from '../../semanticAttributes';
+import { shouldEnableTruncation } from '../ai/utils';
 import type { Event } from '../../types-hoist/event';
 import type { Span, SpanAttributes, SpanAttributeValue, SpanJSON } from '../../types-hoist/span';
 import { spanToJSON } from '../../utils/spanUtils';
@@ -119,7 +120,7 @@ function onVercelAiSpanStart(span: Span): void {
   const integration = client?.getIntegrationByName('VercelAI') as
     | { options?: { enableTruncation?: boolean } }
     | undefined;
-  const enableTruncation = integration?.options?.enableTruncation ?? true;
+  const enableTruncation = shouldEnableTruncation(integration?.options?.enableTruncation);
 
   processGenerateSpan(span, name, attributes, enableTruncation);
 }