diff --git a/README.md b/README.md
index 1e38f3f60..0bf196931 100644
--- a/README.md
+++ b/README.md
@@ -95,7 +95,7 @@ Below is an example `generate_content()` call using `Part` from the `types` modu
 
 ```python
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents=types.Part.from_text(text='Why is the sky blue?')
 )
 ```
@@ -105,7 +105,7 @@ types:
 
 ```python
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents={'text': 'Why is the sky blue?'}
 )
 ```
@@ -367,7 +367,7 @@ See the 'Create a client' section above to initialize a client.
 
 ```python
 response = client.models.generate_content(
-    model='gemini-flash-latest', contents='Why is the sky blue?'
+    model='gemini-3.8-flash', contents='Why is the sky blue?'
 )
 print(response.text)
 ```
@@ -433,7 +433,7 @@ python code.
 ```python
 file = client.files.upload(file='a11.txt')
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents=['Could you summarize this file?', file]
 )
 print(response.text)
@@ -664,7 +664,7 @@ we use `GenerateContentConfig` to specify the desired behavior from the model.
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='high',
     config=types.GenerateContentConfig(
         system_instruction='I say high, you say low',
@@ -697,14 +697,14 @@ client = genai.Client(
 
 # Automatic continuation is enabled by default.
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='Write a comprehensive multi-chapter guide on compiler design.',
 )
 print(response.text)
 
 # Set automatic_continuation=False to disable automatic continuation.
 single_hop_response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='Write a comprehensive multi-chapter guide on compiler design.',
     config=types.GenerateContentConfig(
         automatic_continuation=False,
@@ -751,7 +751,7 @@ print(async_pager[0])
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='Say something bad.',
     config=types.GenerateContentConfig(
         safety_settings=[
@@ -785,7 +785,7 @@ def get_current_weather(location: str) -> str:
 
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='What is the weather like in Boston?',
     config=types.GenerateContentConfig(tools=[get_current_weather]),
 )
@@ -803,7 +803,7 @@ as follows:
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='What is the weather like in Boston?',
     config=types.GenerateContentConfig(
         tools=[get_current_weather],
@@ -850,7 +850,7 @@ function = types.FunctionDeclaration(
 tool = types.Tool(function_declarations=[function])
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='What is the weather like in Boston?',
     config=types.GenerateContentConfig(tools=[tool]),
 )
@@ -894,7 +894,7 @@ function_response_content = types.Content(
 )
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents=[
         user_prompt_content,
         function_call_content,
@@ -929,7 +929,7 @@ def get_current_weather(location: str) -> str:
     return "sunny"
 
 response = client.models.generate_content(
-    model="gemini-flash-latest",
+    model="gemini-3.8-flash",
     contents="What is the weather like in Boston?",
     config=types.GenerateContentConfig(
         tools=[get_current_weather],
@@ -959,7 +959,7 @@ def get_current_weather(location: str) -> str:
     return "sunny"
 
 response = client.models.generate_content(
-    model="gemini-flash-latest",
+    model="gemini-3.8-flash",
     contents="What is the weather like in Boston?",
     config=types.GenerateContentConfig(
         tools=[get_current_weather],
@@ -1010,7 +1010,7 @@ async def run():
 
             # Send request to the model with MCP function declarations
             response = await client.aio.models.generate_content(
-                model="gemini-flash-latest",
+                model="gemini-3.8-flash",
                 contents=prompt,
                 config=genai.types.GenerateContentConfig(
                     tools=[session],  # uses the session, will automatically call the tool using automatic function calling
@@ -1045,7 +1045,7 @@ client = genai.Client(enterprise=True, project=PROJECT_ID, location=LOCATION)
 
 async def agent_platform_mcp():
     response = await client.aio.models.generate_content(
-        model="gemini-flash-latest",
+        model="gemini-3.8-flash",
         contents=f"List my endpoints in {LOCATION} for my {PROJECT_ID} project.",
         config = types.GenerateContentConfig(
             tools=[
@@ -1109,7 +1109,7 @@ user_profile = {
 }
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='Give me a random user profile.',
     config={
         'response_mime_type': 'application/json',
@@ -1139,7 +1139,7 @@ class CountryInfo(BaseModel):
 
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='Give me information for the United States.',
     config=types.GenerateContentConfig(
         response_mime_type='application/json',
@@ -1153,7 +1153,7 @@ print(response.text)
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='Give me information for the United States.',
     config=types.GenerateContentConfig(
         response_mime_type='application/json',
@@ -1192,7 +1192,7 @@ to you, rather than being returned as one chunk.
 
 ```python
 for chunk in client.models.generate_content_stream(
-    model='gemini-flash-latest', contents='Tell me a story in 300 words.'
+    model='gemini-3.8-flash', contents='Tell me a story in 300 words.'
 ):
     print(chunk.text, end='')
 ```
@@ -1206,7 +1206,7 @@ you can use the `from_uri` class method to create a `Part` object.
 from google.genai import types
 
 for chunk in client.models.generate_content_stream(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents=[
         'What is this image about?',
         types.Part.from_uri(
@@ -1230,7 +1230,7 @@ with open(YOUR_IMAGE_PATH, 'rb') as f:
     image_bytes = f.read()
 
 for chunk in client.models.generate_content_stream(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents=[
         'What is this image about?',
         types.Part.from_bytes(data=image_bytes, mime_type=YOUR_IMAGE_MIME_TYPE),
@@ -1249,7 +1249,7 @@ of `client.models.generate_content`
 
 ```python
 response = await client.aio.models.generate_content(
-    model='gemini-flash-latest', contents='Tell me a story in 300 words.'
+    model='gemini-3.8-flash', contents='Tell me a story in 300 words.'
 )
 
 print(response.text)
@@ -1259,7 +1259,7 @@ print(response.text)
 
 ```python
 async for chunk in await client.aio.models.generate_content_stream(
-    model='gemini-flash-latest', contents='Tell me a story in 300 words.'
+    model='gemini-3.8-flash', contents='Tell me a story in 300 words.'
 ):
     print(chunk.text, end='')
 ```
@@ -1268,7 +1268,7 @@ async for chunk in await client.aio.models.generate_content_stream(
 
 ```python
 response = client.models.count_tokens(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='why is the sky blue?',
 )
 print(response)
@@ -1280,7 +1280,7 @@ Compute tokens is only supported in Gemini Enterprise Agent Platform.
 
 ```python
 response = client.models.compute_tokens(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='why is the sky blue?',
 )
 print(response)
@@ -1290,7 +1290,7 @@ print(response)
 
 ```python
 response = await client.aio.models.count_tokens(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='why is the sky blue?',
 )
 print(response)
@@ -1313,7 +1313,7 @@ pip install "google-genai[local-tokenizer-transformers]"
 ```python
 from google.genai import local_tokenizer
 
-tokenizer = local_tokenizer.LocalTokenizer(model_name='gemini-flash-latest')
+tokenizer = local_tokenizer.LocalTokenizer(model_name='gemini-3.8-flash')
 result = tokenizer.count_tokens("What is your name?")
 ```
 
@@ -1322,7 +1322,7 @@ result = tokenizer.count_tokens("What is your name?")
 ```python
 from google.genai import local_tokenizer
 
-tokenizer = local_tokenizer.LocalTokenizer(model_name='gemini-flash-latest')
+tokenizer = local_tokenizer.LocalTokenizer(model_name='gemini-3.8-flash')
 result = tokenizer.compute_tokens("What is your name?")
 ```
 
@@ -1545,7 +1545,7 @@ that it can reflect on its previous responses (i.e., engage in an ongoing
 ### Send Message (Synchronous Non-Streaming)
 
 ```python
-chat = client.chats.create(model='gemini-flash-latest')
+chat = client.chats.create(model='gemini-3.8-flash')
 response = chat.send_message('tell me a story')
 print(response.text)
 response = chat.send_message('summarize the story you told me in 1 sentence')
@@ -1555,7 +1555,7 @@ print(response.text)
 ### Send Message (Synchronous Streaming)
 
 ```python
-chat = client.chats.create(model='gemini-flash-latest')
+chat = client.chats.create(model='gemini-3.8-flash')
 for chunk in chat.send_message_stream('tell me a story'):
     print(chunk.text)
 ```
@@ -1563,7 +1563,7 @@ for chunk in chat.send_message_stream('tell me a story'):
 ### Send Message (Asynchronous Non-Streaming)
 
 ```python
-chat = client.aio.chats.create(model='gemini-flash-latest')
+chat = client.aio.chats.create(model='gemini-3.8-flash')
 response = await chat.send_message('tell me a story')
 print(response.text)
 ```
@@ -1571,7 +1571,7 @@ print(response.text)
 ### Send Message (Asynchronous Streaming)
 
 ```python
-chat = client.aio.chats.create(model='gemini-flash-latest')
+chat = client.aio.chats.create(model='gemini-3.8-flash')
 async for chunk in await chat.send_message_stream('tell me a story'):
     print(chunk.text)
 ```
@@ -1630,7 +1630,7 @@ else:
     file_uris = [file1.uri, file2.uri]
 
 cached_content = client.caches.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     config=types.CreateCachedContentConfig(
         contents=[
             types.Content(
@@ -1665,7 +1665,7 @@ cached_content = client.caches.get(name=cached_content.name)
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     contents='Summarize the pdfs',
     config=types.GenerateContentConfig(
         cached_content=cached_content.name,
@@ -1684,7 +1684,7 @@ See the [documentation site](https://ai.google.dev/gemini-api/docs/interactions)
 
 ```python
 interaction = client.interactions.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     input='Tell me a short joke about programming.'
 )
 print(interaction.output_text)
@@ -1698,14 +1698,14 @@ The Interactions API supports server-side state management. You can continue a c
 ```python
 # 1. First turn
 interaction1 = client.interactions.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     input='Hi, my name is Amir.'
 )
 print(f"Model: {interaction1.output_text}")
 
 # 2. Second turn (passing previous_interaction_id)
 interaction2 = client.interactions.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     input='What is my name?',
     previous_interaction_id=interaction1.id
 )
@@ -1755,7 +1755,7 @@ import base64
 # base64_image = ...
 
 interaction = client.interactions.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     input=[
         {'type': 'text', 'text': 'Describe the image.'},
         {'type': 'image', 'data': base64_image, 'mime_type': 'image/png'}
@@ -1790,7 +1790,7 @@ weather_tool = {
 
 # 2. Send the request with tools
 interaction = client.interactions.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     input='What is the weather in Mountain View, CA?',
     tools=[weather_tool]
 )
@@ -1805,7 +1805,7 @@ for step in (interaction.steps or []):
 
         # Send result back to the model
         interaction = client.interactions.create(
-            model='gemini-flash-latest',
+            model='gemini-3.8-flash',
             previous_interaction_id=interaction.id,
             input=[{
                 'type': 'function_result',
@@ -1825,7 +1825,7 @@ You can also use Google's built-in tools, such as **Google Search** or **Code Ex
 
 ```python
 interaction = client.interactions.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     input='Who won the last Super Bowl?',
     tools=[{'type': 'google_search'}]
 )
@@ -1837,7 +1837,7 @@ print(interaction.output_text)
 
 ```python
 interaction = client.interactions.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     input='Calculate the 50th Fibonacci number.',
     tools=[{'type': 'code_execution'}]
 )
@@ -1897,7 +1897,7 @@ section above to initialize a client.
 ```python
 from google.genai import types
 
-model = 'gemini-flash-latest'
+model = 'gemini-3.8-flash'
 training_dataset = types.TuningDataset(
     # or gcs_uri=my_enterprise_multimodal_dataset
     gcs_uri='gs://your-gcs-bucket/your-tuning-data.jsonl',
@@ -2051,7 +2051,7 @@ Gemini Enterprise Agent Platform:
 ```python
 # Specify model and source file only, destination and job display name will be auto-populated
 job = client.batches.create(
-    model='gemini-flash-latest',
+    model='gemini-3.8-flash',
     src='bq://my-project.my-dataset.my-table',  # or "gs://path/to/input/data"
 )
 
@@ -2063,7 +2063,7 @@ Gemini Developer API:
 ```python
 # Create a batch job with inlined requests
 batch_job = client.batches.create(
-    model="gemini-flash-latest",
+    model="gemini-3.8-flash",
     src=[{
         "contents": [{
             "parts": [{
@@ -2098,7 +2098,7 @@ file = client.files.upload(
 
 # Create a batch job with file name
 batch_job = client.batches.create(
-    model="gemini-flash-latest",
+    model="gemini-3.8-flash",
     src="files/test-json",
 )
 ```
@@ -2200,7 +2200,7 @@ The structure of the dictionary must match the backend API's request structure.
 
 ```python
 response = client.models.generate_content(
-    model="gemini-flash-latest",
+    model="gemini-3.8-flash",
     contents="What is the weather in Boston? and how about Sunnyvale?",
     config=types.GenerateContentConfig(
         tools=[get_current_weather],
diff --git a/docs/source/index.rst b/docs/source/index.rst
index 60dc7f62b..0ba6b1fce 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -302,7 +302,7 @@ with text content input (text output)
 .. code:: python
 
     response = client.models.generate_content(
-        model='gemini-flash-latest', contents='Why is the sky blue?'
+        model='gemini-3.8-flash', contents='Why is the sky blue?'
     )
     print(response.text)
 
@@ -374,7 +374,7 @@ python code.
 
     file = client.files.upload(file='a11.txt')
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=['Could you summarize this file?', file]
     )
     print(response.text)
@@ -614,7 +614,7 @@ and `Gemini API docs <https://aistudio.google.com/docs/models>`_ respectively.
     from google.genai import types
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='high',
         config=types.GenerateContentConfig(
             system_instruction='I say high, you say low',
@@ -635,7 +635,7 @@ dictionaries. You can get the type from ``google.genai.types``.
     from google.genai import types
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=types.Part.from_text(text='Why is the sky blue?'),
         config=types.GenerateContentConfig(
             temperature=0,
@@ -694,7 +694,7 @@ Safety Settings
     from google.genai import types
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='Say something bad.',
         config=types.GenerateContentConfig(
             safety_settings=[
@@ -730,7 +730,7 @@ called and responded by default.
 
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='What is the weather like in Boston?',
         config=types.GenerateContentConfig(
             tools=[get_current_weather],
@@ -751,7 +751,7 @@ as follows:
     from google.genai import types
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='What is the weather like in Boston?',
         config=types.GenerateContentConfig(
             tools=[get_current_weather],
@@ -800,7 +800,7 @@ Then you will receive a function call part in the response.
     tool = types.Tool(function_declarations=[function])
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='What is the weather like in Boston?',
         config=types.GenerateContentConfig(
             tools=[tool],
@@ -845,7 +845,7 @@ The following example shows how to do it for a simple function invocation.
     )
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=[
             user_prompt_content,
             function_call_content,
@@ -882,7 +882,7 @@ If you'd like to disable automatic function calling in `ANY` mode:
         return "sunny"
 
     response = client.models.generate_content(
-        model="gemini-flash-latest",
+        model="gemini-3.8-flash",
         contents="What is the weather like in Boston?",
         config=types.GenerateContentConfig(
             tools=[get_current_weather],
@@ -912,7 +912,7 @@ Assuming you prefer ``1`` turn for automatic function calling:
         return "sunny"
 
     response = client.models.generate_content(
-        model="gemini-flash-latest",
+        model="gemini-3.8-flash",
         contents="What is the weather like in Boston?",
         config=types.GenerateContentConfig(
             tools=[get_current_weather],
@@ -960,7 +960,7 @@ experimental feature. You can pass a local MCP server as a tool directly.
 
                 # Send request to the model with MCP function declarations
                 response = await client.aio.models.generate_content(
-                    model="gemini-flash-latest",
+                    model="gemini-3.8-flash",
                     contents=prompt,
                     config=genai.types.GenerateContentConfig(
                         temperature=0,
@@ -1008,7 +1008,7 @@ Schemas can be provided as standard JSON schema.
     }
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='Give me a random user profile.',
         config={
             'response_mime_type': 'application/json',
@@ -1040,7 +1040,7 @@ Schemas can be provided as Pydantic Models.
 
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='Give me information for the United States.',
         config=types.GenerateContentConfig(
             response_mime_type='application/json',
@@ -1054,7 +1054,7 @@ Schemas can be provided as Pydantic Models.
     from google.genai import types
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='Give me information for the United States.',
         config=types.GenerateContentConfig(
             response_mime_type='application/json',
@@ -1104,7 +1104,7 @@ values as the response.
         KEYBOARD = 'Keyboard'
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='What instrument plays multiple notes at once?',
         config={
             'response_mime_type': 'text/x.enum',
@@ -1131,7 +1131,7 @@ identical but in quotes.
         KEYBOARD = 'Keyboard'
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='What instrument plays multiple notes at once?',
         config={
             'response_mime_type': 'application/json',
@@ -1152,7 +1152,7 @@ Streaming for text content
 .. code:: python
 
     for chunk in client.models.generate_content_stream(
-        model='gemini-flash-latest', contents='Tell me a story in 300 words.'
+        model='gemini-3.8-flash', contents='Tell me a story in 300 words.'
     ):
         print(chunk.text, end='')
 
@@ -1166,7 +1166,7 @@ If your image is stored in `Google Cloud Storage <https://cloud.google.com/stora
     from google.genai import types
 
     for chunk in client.models.generate_content_stream(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=[
             'What is this image about?',
             types.Part.from_uri(
@@ -1191,7 +1191,7 @@ data and use the ``from_bytes`` class method to create a ``Part`` object.
         image_bytes = f.read()
 
     for chunk in client.models.generate_content_stream(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=[
             'What is this image about?',
             types.Part.from_bytes(data=image_bytes, mime_type=YOUR_IMAGE_MIME_TYPE),
@@ -1210,7 +1210,7 @@ For example, ``client.aio.models.generate_content`` is the ``async`` version of
 .. code:: python
 
     response = await client.aio.models.generate_content(
-        model='gemini-flash-latest', contents='Tell me a story in 300 words.'
+        model='gemini-3.8-flash', contents='Tell me a story in 300 words.'
     )
 
     print(response.text)
@@ -1221,7 +1221,7 @@ Generate Content (Asynchronous Streaming)
 .. code:: python
 
     async for chunk in await client.aio.models.generate_content_stream(
-        model='gemini-flash-latest', contents='Tell me a story in 300 words.'
+        model='gemini-3.8-flash', contents='Tell me a story in 300 words.'
     ):
         print(chunk.text, end='')
 
@@ -1231,7 +1231,7 @@ Count Tokens and Compute Tokens
 .. code:: python
 
     response = client.models.count_tokens(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='why is the sky blue?',
     )
     print(response)
@@ -1244,7 +1244,7 @@ Compute tokens is only supported in Gemini Enterprise Agent Platform.
 .. code:: python
 
     response = client.models.compute_tokens(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='why is the sky blue?',
     )
     print(response)
@@ -1255,7 +1255,7 @@ Count Tokens (Asynchronous)
 .. code:: python
 
     response = await client.aio.models.count_tokens(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='why is the sky blue?',
     )
     print(response)
@@ -1519,7 +1519,7 @@ Send Message (Synchronous Non-Streaming)
 
 .. code:: python
 
-    chat = client.chats.create(model='gemini-flash-latest')
+    chat = client.chats.create(model='gemini-3.8-flash')
     response = chat.send_message('tell me a story')
     print(response.text)
     response = chat.send_message('summarize the story you told me in 1 sentence')
@@ -1530,7 +1530,7 @@ Send Message (Synchronous Streaming)
 
 .. code:: python
 
-    chat = client.chats.create(model='gemini-flash-latest')
+    chat = client.chats.create(model='gemini-3.8-flash')
     for chunk in chat.send_message_stream('tell me a story'):
         print(chunk.text)
 
@@ -1539,7 +1539,7 @@ Send Message (Asynchronous Non-Streaming)
 
 .. code:: python
 
-    chat = client.aio.chats.create(model='gemini-flash-latest')
+    chat = client.aio.chats.create(model='gemini-3.8-flash')
     response = await chat.send_message('tell me a story')
     print(response.text)
 
@@ -1548,7 +1548,7 @@ Send Message (Asynchronous Streaming)
 
 .. code:: python
 
-    chat = client.aio.chats.create(model='gemini-flash-latest')
+    chat = client.aio.chats.create(model='gemini-3.8-flash')
     async for chunk in await chat.send_message_stream('tell me a story'):
         print(chunk.text)
 
@@ -1614,7 +1614,7 @@ Create
         file_uris = [file1.uri, file2.uri]
 
     cached_content = client.caches.create(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         config=types.CreateCachedContentConfig(
             contents=[
                 types.Content(
@@ -1651,7 +1651,7 @@ Generate Content with Caches
     from google.genai import types
 
     response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='Summarize the pdfs',
         config=types.GenerateContentConfig(
             cached_content=cached_content.name,
@@ -1671,7 +1671,7 @@ Basic Interaction
 .. code:: python
 
     interaction = client.interactions.create(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         input='Tell me a short joke about programming.'
     )
     print(interaction.output_text)
@@ -1685,14 +1685,14 @@ The Interactions API supports server-side state management. You can continue a c
 
     # 1. First turn
     interaction1 = client.interactions.create(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         input='Hi, my name is Amir.'
     )
     print(f"Model: {interaction1.output_text}")
 
     # 2. Second turn (passing previous_interaction_id)
     interaction2 = client.interactions.create(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         input='What is my name?',
         previous_interaction_id=interaction1.id,
     )
@@ -1743,7 +1743,7 @@ You can use Google's built-in tools such as Google Search or Code Execution.
 .. code:: python
 
     interaction = client.interactions.create(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         input='Who won the last Super Bowl?',
         tools=[{'type': 'google_search'}],
     )
@@ -1765,7 +1765,7 @@ Tune
 
     from google.genai import types
 
-    model = 'gemini-flash-latest'
+    model = 'gemini-3.8-flash'
     training_dataset = types.TuningDataset(
         # or gcs_uri=my_enterprise_multimodal_dataset
         gcs_uri='gs://your-gcs-bucket/your-tuning-data.jsonl',
@@ -1946,7 +1946,7 @@ Vertex AI client support using a BigQuery table or a GCS file as the source.
 
     # Specify model and source file only, destination and job display name will be auto-populated
     job = client.batches.create(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         src='bq://my-project.my-dataset.my-table',  # or "gs://path/to/input/data"
     )
 
@@ -1960,7 +1960,7 @@ Gemini Developer API
 
     # Create a batch job with inlined requests
     batch_job = client.batches.create(
-        model="gemini-flash-latest",
+        model="gemini-3.8-flash",
         src=[{
             "contents": [{
                 "parts": [{
@@ -1996,7 +1996,7 @@ Then upload the file.
     )
     # Create a batch job with file name
     batch_job = client.batches.create(
-        model="gemini-flash-latest",
+        model="gemini-3.8-flash",
         src="files/test-json",
     )
 
@@ -2118,7 +2118,7 @@ The structure of the dictionary must match the backend API's request structure.
 .. code:: python
 
     response = client.models.generate_content(
-        model="gemini-flash-latest",
+        model="gemini-3.8-flash",
         contents="What is the weather in Boston? and how about Sunnyvale?",
         config=types.GenerateContentConfig(
             tools=[get_current_weather],
diff --git a/google/genai/batches.py b/google/genai/batches.py
index a6050dad3..fdbf64e92 100644
--- a/google/genai/batches.py
+++ b/google/genai/batches.py
@@ -2295,7 +2295,7 @@ def create(
     .. code-block:: python
 
       batch_job = client.batches.create(
-          model="gemini-flash-latest",
+          model="gemini-3.8-flash",
           src="gs://path/to/input/data",
       )
       print(batch_job.state)
@@ -2925,7 +2925,7 @@ async def create(
     .. code-block:: python
 
       batch_job = await client.aio.batches.create(
-          model="gemini-flash-latest",
+          model="gemini-3.8-flash",
           src="gs://path/to/input/data",
       )
     """
diff --git a/google/genai/chats.py b/google/genai/chats.py
index 9b4088ad2..5dd6c3503 100644
--- a/google/genai/chats.py
+++ b/google/genai/chats.py
@@ -245,7 +245,7 @@ def send_message(
 
     .. code-block:: python
 
-      chat = client.chats.create(model='gemini-flash-latest')
+      chat = client.chats.create(model='gemini-3.8-flash')
       response = chat.send_message('tell me a story')
     """
 
@@ -418,7 +418,7 @@ def send_message_stream(
 
     .. code-block:: python
 
-      chat = client.chats.create(model='gemini-flash-latest')
+      chat = client.chats.create(model='gemini-3.8-flash')
       for chunk in chat.send_message_stream('tell me a story'):
         print(chunk.text)
     """
@@ -657,7 +657,7 @@ async def send_message(
 
     .. code-block:: python
 
-      chat = client.aio.chats.create(model='gemini-flash-latest')
+      chat = client.aio.chats.create(model='gemini-3.8-flash')
       response = await chat.send_message('tell me a story')
     """
     method_config = config if config else self._config
@@ -913,7 +913,7 @@ async def send_message_stream(
 
     .. code-block:: python
 
-      chat = client.aio.chats.create(model='gemini-flash-latest')
+      chat = client.aio.chats.create(model='gemini-3.8-flash')
       async for chunk in await chat.send_message_stream('tell me a story'):
         print(chunk.text)
     """
diff --git a/google/genai/client.py b/google/genai/client.py
index a4a3bf692..201b49acc 100644
--- a/google/genai/client.py
+++ b/google/genai/client.py
@@ -245,11 +245,11 @@ async def aclose(self) -> None:
           enterprise=True, project='my-project-id', location='us-central1'
       ).aio
       response_1 = await async_client.models.generate_content(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='Hello World',
       )
       response_2 = await async_client.models.generate_content(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='Hello World',
       )
       # Close the client to release resources.
@@ -641,11 +641,11 @@ def close(self) -> None:
           enterprise=True, project='my-project-id', location='us-central1'
       )
       response_1 = client.models.generate_content(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='Hello World',
       )
       response_2 = client.models.generate_content(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='Hello World',
       )
       # Close the client to release resources.
diff --git a/google/genai/models.py b/google/genai/models.py
index 2e8a4ee50..ddb378e50 100644
--- a/google/genai/models.py
+++ b/google/genai/models.py
@@ -5426,7 +5426,7 @@ def count_tokens(
     .. code-block:: python
 
       response = client.models.count_tokens(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='What is your name?',
       )
       print(response)
@@ -5537,7 +5537,7 @@ def compute_tokens(
     .. code-block:: python
 
       response = client.models.compute_tokens(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='What is your name?',
       )
       print(response)
@@ -5836,18 +5836,18 @@ def generate_content(
 
     For the `model` parameter, supported formats for Gemini Enterprise Agent
     Platform API include:
-    - The Gemini model ID, for example: 'gemini-flash-latest'
+    - The Gemini model ID, for example: 'gemini-3.8-flash'
     - The full resource name starts with 'projects/', for example:
-      'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-flash-latest'
+      'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-3.8-flash'
     - The partial resource name with 'publishers/', for example:
-      'publishers/google/models/gemini-flash-latest' or
+      'publishers/google/models/gemini-3.8-flash' or
     - `/` separated publisher and model name, for example:
-      'google/gemini-flash-latest'
+      'google/gemini-3.8-flash'
 
     For the `model` parameter, supported formats for Gemini API include:
-    - The Gemini model ID, for example: 'gemini-flash-latest'
+    - The Gemini model ID, for example: 'gemini-3.8-flash'
     - The model name starts with 'models/', for example:
-      'models/gemini-flash-latest'
+      'models/gemini-3.8-flash'
     - For tuned models, the model name starts with 'tunedModels/',
       for example:
       'tunedModels/1234567890123456789'
@@ -5876,7 +5876,7 @@ def generate_content(
       )
 
       response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='''What is a good name for a flower shop that specializes in
           selling bouquets of dried flowers?'''
       )
@@ -5887,7 +5887,7 @@ def generate_content(
       # * Timeless Petals
 
       response = client.models.generate_content(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=[
           types.Part.from_text(text='What is shown in this image?'),
           types.Part.from_uri(file_uri='gs://generativeai-downloads/images/scones.jpg',
@@ -6015,18 +6015,18 @@ def generate_content_stream(
 
     For the `model` parameter, supported formats for Gemini Enterprise Agent
     Platform API include:
-    - The Gemini model ID, for example: 'gemini-flash-latest'
+    - The Gemini model ID, for example: 'gemini-3.8-flash'
     - The full resource name starts with 'projects/', for example:
-      'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-flash-latest'
+      'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-3.8-flash'
     - The partial resource name with 'publishers/', for example:
-      'publishers/google/models/gemini-flash-latest' or
+      'publishers/google/models/gemini-3.8-flash' or
     - `/` separated publisher and model name, for example:
-      'google/gemini-flash-latest'
+      'google/gemini-3.8-flash'
 
     For the `model` parameter, supported formats for Gemini API include:
-    - The Gemini model ID, for example: 'gemini-flash-latest'
+    - The Gemini model ID, for example: 'gemini-3.8-flash'
     - The model name starts with 'models/', for example:
-      'models/gemini-flash-latest'
+      'models/gemini-3.8-flash'
     - For tuned models, the model name starts with 'tunedModels/',
       for example:
       'tunedModels/1234567890123456789'
@@ -6056,7 +6056,7 @@ def generate_content_stream(
       )
 
       for chunk in client.models.generate_content_stream(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='''What is a good name for a flower shop that specializes in
           selling bouquets of dried flowers?'''
       ):
@@ -6067,7 +6067,7 @@ def generate_content_stream(
       # * Timeless Petals
 
       for chunk in client.models.generate_content_stream(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=[
           types.Part.from_text('What is shown in this image?'),
           types.Part.from_uri('gs://generativeai-downloads/images/scones.jpg',
@@ -6532,7 +6532,7 @@ def list(
 
       response=client.models.list(config={'page_size': 5, 'query_base': True})
       print(response.page)
-      # [Model(name='publishers/google/models/gemini-flash-latest' ...
+      # [Model(name='publishers/google/models/gemini-3.8-flash' ...
     """
 
     config = (
@@ -7705,7 +7705,7 @@ async def count_tokens(
     .. code-block:: python
 
       response = await client.aio.models.count_tokens(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='What is your name?',
       )
       print(response)
@@ -7815,7 +7815,7 @@ async def compute_tokens(
     .. code-block:: python
 
       response = await client.aio.models.compute_tokens(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='What is your name?',
       )
       print(response)
@@ -8067,7 +8067,7 @@ async def generate_content(
       )
 
       response = await client.aio.models.generate_content(
-          model='gemini-flash-latest',
+          model='gemini-3.8-flash',
           contents='User input: I like bagels. Answer:',
           config=types.GenerateContentConfig(
               system_instruction=
@@ -8269,18 +8269,18 @@ async def generate_content_stream(
 
     For the `model` parameter, supported formats for Gemini Enterprise Agent
     Platform API include:
-    - The Gemini model ID, for example: 'gemini-flash-latest'
+    - The Gemini model ID, for example: 'gemini-3.8-flash'
     - The full resource name starts with 'projects/', for example:
-      'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-flash-latest'
+      'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-3.8-flash'
     - The partial resource name with 'publishers/', for example:
-      'publishers/google/models/gemini-flash-latest' or
+      'publishers/google/models/gemini-3.8-flash' or
     - `/` separated publisher and model name, for example:
-      'google/gemini-flash-latest'
+      'google/gemini-3.8-flash'
 
     For the `model` parameter, supported formats for Gemini API include:
-    - The Gemini model ID, for example: 'gemini-flash-latest'
+    - The Gemini model ID, for example: 'gemini-3.8-flash'
     - The model name starts with 'models/', for example:
-      'models/gemini-flash-latest'
+      'models/gemini-3.8-flash'
     - For tuned models, the model name starts with 'tunedModels/',
       for example:
       'tunedModels/1234567890123456789'
@@ -8310,7 +8310,7 @@ async def generate_content_stream(
       )
 
       async for chunk in await client.aio.models.generate_content_stream(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents='''What is a good name for a flower shop that specializes in
           selling bouquets of dried flowers?'''
       ):
@@ -8321,7 +8321,7 @@ async def generate_content_stream(
       # * Timeless Petals
 
       async for chunk in await client.aio.models.generate_content_stream(
-        model='gemini-flash-latest',
+        model='gemini-3.8-flash',
         contents=[
           types.Part.from_text('What is shown in this image?'),
           types.Part.from_uri('gs://generativeai-downloads/images/scones.jpg',
@@ -8627,7 +8627,7 @@ async def list(
           config={'page_size': 5, 'query_base': True}
         )
       print(response.page)
-      # [Model(name='publishers/google/models/gemini-flash-latest' ...
+      # [Model(name='publishers/google/models/gemini-3.8-flash' ...
     """
 
     config = (
diff --git a/google/genai/types.py b/google/genai/types.py
index 6055e1363..e37c171ba 100644
--- a/google/genai/types.py
+++ b/google/genai/types.py
@@ -16408,7 +16408,7 @@ class _CreateTuningJobParametersPrivate(_common.BaseModel):
 
   base_model: Optional[str] = Field(
       default=None,
-      description="""The base model that is being tuned, e.g., "gemini-flash-latest".""",
+      description="""The base model that is being tuned, e.g., "gemini-3.8-flash".""",
   )
   pre_tuned_model: Optional[PreTunedModel] = Field(
       default=None, description="""The PreTunedModel that is being tuned."""
@@ -16426,7 +16426,7 @@ class _CreateTuningJobParametersPrivateDict(TypedDict, total=False):
   """Fine-tuning job creation parameters - optional fields."""
 
   base_model: Optional[str]
-  """The base model that is being tuned, e.g., "gemini-flash-latest"."""
+  """The base model that is being tuned, e.g., "gemini-3.8-flash"."""
 
   pre_tuned_model: Optional[PreTunedModelDict]
   """The PreTunedModel that is being tuned."""
@@ -16768,7 +16768,7 @@ class _CreateCachedContentParameters(_common.BaseModel):
 
   model: Optional[str] = Field(
       default=None,
-      description="""ID of the model to use. Example: gemini-flash-latest""",
+      description="""ID of the model to use. Example: gemini-3.8-flash""",
   )
   config: Optional[CreateCachedContentConfig] = Field(
       default=None,
@@ -16781,7 +16781,7 @@ class _CreateCachedContentParametersDict(TypedDict, total=False):
   """Parameters for caches.create method."""
 
   model: Optional[str]
-  """ID of the model to use. Example: gemini-flash-latest"""
+  """ID of the model to use. Example: gemini-3.8-flash"""
 
   config: Optional[CreateCachedContentConfigDict]
   """Configuration that contains optional parameters.
@@ -23042,7 +23042,7 @@ class CreateTuningJobParameters(_common.BaseModel):
 
   base_model: Optional[str] = Field(
       default=None,
-      description="""The base model that is being tuned, e.g., "gemini-flash-latest".""",
+      description="""The base model that is being tuned, e.g., "gemini-3.8-flash".""",
   )
   training_dataset: Optional[TuningDataset] = Field(
       default=None,
@@ -23057,7 +23057,7 @@ class CreateTuningJobParametersDict(TypedDict, total=False):
   """Fine-tuning job creation parameters - optional fields."""
 
   base_model: Optional[str]
-  """The base model that is being tuned, e.g., "gemini-flash-latest"."""
+  """The base model that is being tuned, e.g., "gemini-3.8-flash"."""
 
   training_dataset: Optional[TuningDatasetDict]
   """Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file."""