diff --git a/docs/async_client.md b/docs/async_client.md
index cc4c5806504..891a2356731 100644
--- a/docs/async_client.md
+++ b/docs/async_client.md
@@ -292,7 +292,7 @@ client = AsyncClient(provider=g4f.Provider.OpenaiChat)
 
 response = await client.chat.completions.create(
     model="gpt-4",
-    provider=g4f.Provider.Bing,
+    provider=g4f.Provider.CopilotAccount,
     messages=[
         {
             "role": "user",
diff --git a/docs/legacy.md b/docs/legacy.md
index d5cd5a36a2d..393e3c397b5 100644
--- a/docs/legacy.md
+++ b/docs/legacy.md
@@ -7,7 +7,7 @@ import g4f
 
 g4f.debug.logging = True  # Enable debug logging
 g4f.debug.version_check = False  # Disable automatic version checking
-print(g4f.Provider.Bing.params)  # Print supported args for Bing
+print(g4f.Provider.Gemini.params)  # Print supported args for Bing
 
 # Using automatic a provider for the given model
 ## Streamed completion
@@ -78,7 +78,7 @@ for message in response:
 
 Image upload and generation are supported by three main providers:
 
-- **Bing & Other GPT-4 Providers:** Utilizes Microsoft's Image Creator.
+- **Microsoft Copilot & Other GPT-4 Providers:** Utilizes Microsoft's Image Creator.
 - **Google Gemini:** Available for free accounts with IP addresses outside Europe.
 - **OpenaiChat with GPT-4:** Accessible for users with a Plus subscription.
 
diff --git a/etc/unittest/client.py b/etc/unittest/client.py
index 97f9f6c8dc4..663d5f282eb 100644
--- a/etc/unittest/client.py
+++ b/etc/unittest/client.py
@@ -2,7 +2,10 @@
 
 import unittest
 
-from g4f.client import Client, AsyncClient, ChatCompletion, ChatCompletionChunk
+from g4f.errors import ModelNotFoundError
+from g4f.client import Client, AsyncClient, ChatCompletion, ChatCompletionChunk, get_model_and_provider
+from g4f.Provider.Copilot import Copilot
+from g4f.models import gpt_4o
 from .mocks import AsyncGeneratorProviderMock, ModelProviderMock, YieldProviderMock
 
 DEFAULT_MESSAGES = [{'role': 'user', 'content': 'Hello'}]
@@ -104,5 +107,35 @@ def test_stop(self):
         self.assertIsInstance(response, ChatCompletion)
         self.assertEqual("How are you?", response.choices[0].message.content)
 
+    def test_model_not_found(self):
+        def run_exception():
+            client = Client()
+            client.chat.completions.create(DEFAULT_MESSAGES, "Hello")
+        self.assertRaises(ModelNotFoundError, run_exception)
+
+    def test_best_provider(self):
+        not_default_model = "gpt-4o"
+        model, provider = get_model_and_provider(not_default_model, None, False)
+        self.assertTrue(hasattr(provider, "create_completion"))
+        self.assertEqual(model, not_default_model)
+
+    def test_default_model(self):
+        default_model = ""
+        model, provider = get_model_and_provider(default_model, None, False)
+        self.assertTrue(hasattr(provider, "create_completion"))
+        self.assertEqual(model, default_model)
+
+    def test_provider_as_model(self):
+        provider_as_model = Copilot.__name__
+        model, provider = get_model_and_provider(provider_as_model, None, False)
+        self.assertTrue(hasattr(provider, "create_completion"))
+        self.assertIsInstance(model, str)
+        self.assertEqual(model, Copilot.default_model)
+
+    def test_get_model(self):
+        model, provider = get_model_and_provider(gpt_4o.name, None, False)
+        self.assertTrue(hasattr(provider, "create_completion"))
+        self.assertEqual(model, gpt_4o.name)
+
 if __name__ == '__main__':
     unittest.main()
\ No newline at end of file
diff --git a/etc/unittest/main.py b/etc/unittest/main.py
index a3949216fff..0c71aea10bf 100644
--- a/etc/unittest/main.py
+++ b/etc/unittest/main.py
@@ -1,7 +1,9 @@
 import unittest
 import asyncio
+
 import g4f
 from g4f import ChatCompletion, get_last_provider
+from g4f.errors import VersionNotFoundError
 from g4f.Provider import RetryProvider
 from .mocks import ProviderMock
 
@@ -27,4 +29,11 @@ def test_get_last_provider_as_dict(self):
         last_provider_dict = get_last_provider(True)
         self.assertIsInstance(last_provider_dict, dict)
         self.assertIn('name', last_provider_dict)
-        self.assertEqual(ProviderMock.__name__, last_provider_dict['name'])
\ No newline at end of file
+        self.assertEqual(ProviderMock.__name__, last_provider_dict['name'])
+
+    def test_get_latest_version(self):
+        try:
+            self.assertIsInstance(g4f.version.utils.current_version, str)
+        except VersionNotFoundError:
+            pass
+        self.assertIsInstance(g4f.version.utils.latest_version, str)
\ No newline at end of file
diff --git a/g4f/Provider/ChatGpt.py b/g4f/Provider/ChatGpt.py
index 02bbbcc4166..ebfc7c2d9f7 100644
--- a/g4f/Provider/ChatGpt.py
+++ b/g4f/Provider/ChatGpt.py
@@ -205,6 +205,7 @@ def create_completion(
         
         response = session.post('https://chatgpt.com/backend-anon/conversation',
                                  headers=headers, json=json_data, stream=True)
+        response.raise_for_status()
 
         replace = ''
         for line in response.iter_lines():
diff --git a/g4f/Provider/Copilot.py b/g4f/Provider/Copilot.py
index 5721f37701e..3c431df20e7 100644
--- a/g4f/Provider/Copilot.py
+++ b/g4f/Provider/Copilot.py
@@ -23,7 +23,7 @@
 from ..errors import MissingRequirementsError
 from ..requests.raise_for_status import raise_for_status
 from ..providers.asyncio import get_running_loop
-from ..Provider.openai.har_file import NoValidHarFileError, get_headers
+from ..Provider.openai.har_file import NoValidHarFileError, get_headers, get_har_files
 from ..requests import get_nodriver
 from ..image import ImageResponse, to_bytes, is_accepted_format
 from ..cookies import get_cookies_dir
@@ -188,16 +188,9 @@ async def get_access_token_and_cookies(cls, proxy: str = None):
         return access_token, cookies
 
 def readHAR():
-    harPath = []
-    for root, _, files in os.walk(get_cookies_dir()):
-        for file in files:
-            if file.endswith(".har"):
-                harPath.append(os.path.join(root, file))
-    if not harPath:
-        raise NoValidHarFileError("No .har file found")
     api_key = None
     cookies = None
-    for path in harPath:
+    for path in get_har_files():
         with open(path, 'rb') as file:
             try:
                 harFile = json.loads(file.read())
diff --git a/g4f/Provider/needs_auth/OpenaiChat.py b/g4f/Provider/needs_auth/OpenaiChat.py
index 37bdf0742c8..392d4d5da62 100644
--- a/g4f/Provider/needs_auth/OpenaiChat.py
+++ b/g4f/Provider/needs_auth/OpenaiChat.py
@@ -424,10 +424,10 @@ async def iter_messages_line(cls, session: StreamSession, line: bytes, fields: C
                         for element in c.get("parts"):
                             if isinstance(element, dict) and element.get("content_type") == "image_asset_pointer":
                                 image = cls.get_generated_image(session, cls._headers, element)
-                                if image is not None:
-                                    generated_images.append(image)
+                                generated_images.append(image)
                         for image_response in await asyncio.gather(*generated_images):
-                            yield image_response
+                            if image_response is not None:
+                                yield image_response
                     if m.get("author", {}).get("role") == "assistant":
                         fields.message_id = v.get("message", {}).get("id")
             return
diff --git a/g4f/Provider/openai/har_file.py b/g4f/Provider/openai/har_file.py
index e863b6acf77..819952cda14 100644
--- a/g4f/Provider/openai/har_file.py
+++ b/g4f/Provider/openai/har_file.py
@@ -45,7 +45,7 @@ def __init__(self, arkURL, arkBx, arkHeader, arkBody, arkCookies, userAgent):
         self.arkCookies = arkCookies
         self.userAgent = userAgent
 
-def readHAR():
+def get_har_files():
     harPath = []
     for root, _, files in os.walk(get_cookies_dir()):
         for file in files:
@@ -53,7 +53,11 @@ def readHAR():
                 harPath.append(os.path.join(root, file))
     if not harPath:
         raise NoValidHarFileError("No .har file found")
-    for path in harPath:
+    harPath.sort(key=lambda x: os.path.getmtime(x))
+    return harPath
+
+def readHAR():
+    for path in get_har_files():
         with open(path, 'rb') as file:
             try:
                 harFile = json.loads(file.read())
diff --git a/g4f/client/__init__.py b/g4f/client/__init__.py
index 86a810493b9..0b01fe0ff6a 100644
--- a/g4f/client/__init__.py
+++ b/g4f/client/__init__.py
@@ -8,7 +8,6 @@
 import base64
 from typing import Union, AsyncIterator, Iterator, Coroutine, Optional
 
-from ..providers.base_provider import AsyncGeneratorProvider
 from ..image import ImageResponse, copy_images, images_dir
 from ..typing import Messages, Image, ImageType
 from ..providers.types import ProviderType
@@ -58,7 +57,7 @@ def iter_response(
         elif isinstance(chunk, BaseConversation):
             yield chunk
             continue
-        elif isinstance(chunk, SynthesizeData):
+        elif isinstance(chunk, SynthesizeData) or chunk is None:
             continue
 
         chunk = str(chunk)
@@ -121,7 +120,7 @@ async def async_iter_response(
             elif isinstance(chunk, BaseConversation):
                 yield chunk
                 continue
-            elif isinstance(chunk, SynthesizeData):
+            elif isinstance(chunk, SynthesizeData) or chunk is None:
                 continue
 
             chunk = str(chunk)
@@ -292,6 +291,7 @@ async def async_generate(
         **kwargs
     ) -> ImagesResponse:
         provider_handler = await self.get_provider_handler(model, provider, BingCreateImages)
+        provider_name = provider.__name__ if hasattr(provider, "__name__") else type(provider).__name__
         if proxy is None:
             proxy = self.client.proxy
 
@@ -317,17 +317,17 @@ async def async_generate(
                     response = item
                     break
         else:
-            raise ValueError(f"Provider {getattr(provider_handler, '__name__')} does not support image generation")
+            raise ValueError(f"Provider {provider_name} does not support image generation")
         if isinstance(response, ImageResponse):
             return await self._process_image_response(
                 response,
                 response_format,
                 proxy,
                 model,
-                getattr(provider_handler, "__name__", None)
+                provider_name
             )
         if response is None:
-            raise NoImageResponseError(f"No image response from {getattr(provider_handler, '__name__')}")
+            raise NoImageResponseError(f"No image response from {provider_name}")
         raise NoImageResponseError(f"Unexpected response type: {type(response)}")
 
     def create_variation(
@@ -352,6 +352,7 @@ async def async_create_variation(
         **kwargs
     ) -> ImagesResponse:
         provider_handler = await self.get_provider_handler(model, provider, OpenaiAccount)
+        provider_name = provider.__name__ if hasattr(provider, "__name__") else type(provider).__name__
         if proxy is None:
             proxy = self.client.proxy
 
@@ -372,14 +373,14 @@ async def async_create_variation(
             else:
                 response = provider_handler.create_variation(image, model=model, response_format=response_format, proxy=proxy, **kwargs)
         else:
-            raise NoImageResponseError(f"Provider {provider} does not support image variation")
-    
+            raise NoImageResponseError(f"Provider {provider_name} does not support image variation")
+
         if isinstance(response, str):
             response = ImageResponse([response])
         if isinstance(response, ImageResponse):
-            return self._process_image_response(response, response_format, proxy, model, getattr(provider, "__name__", None))
+            return self._process_image_response(response, response_format, proxy, model, provider_name)
         if response is None:
-            raise NoImageResponseError(f"No image response from {getattr(provider, '__name__')}")
+            raise NoImageResponseError(f"No image response from {provider_name}")
         raise NoImageResponseError(f"Unexpected response type: {type(response)}")
 
     async def _process_image_response(
diff --git a/g4f/client/service.py b/g4f/client/service.py
index 44533ece9d3..7fd089d43a2 100644
--- a/g4f/client/service.py
+++ b/g4f/client/service.py
@@ -61,18 +61,26 @@ def get_model_and_provider(model    : Union[Model, str],
     if not provider:
         if not model:
             model = default
+            provider = model.best_provider
         elif isinstance(model, str):
-            raise ModelNotFoundError(f'Model not found: {model}')
-        provider = model.best_provider
+            if model in ProviderUtils.convert:
+                provider = ProviderUtils.convert[model]
+                model = provider.default_model if hasattr(provider, "default_model") else ""
+            else:
+                raise ModelNotFoundError(f'Model not found: {model}')
+        else:
+            provider = model.best_provider
 
     if not provider:
         raise ProviderNotFoundError(f'No provider found for model: {model}')
 
+    provider_name = provider.__name__ if hasattr(provider, "__name__") else type(provider).__name__
+
     if isinstance(model, Model):
         model = model.name
 
     if not ignore_working and not provider.working:
-        raise ProviderNotWorkingError(f'{provider.__name__} is not working')
+        raise ProviderNotWorkingError(f"{provider_name} is not working")
 
     if isinstance(provider, BaseRetryProvider):
         if not ignore_working:
@@ -81,12 +89,12 @@ def get_model_and_provider(model    : Union[Model, str],
             provider.providers = [p for p in provider.providers if p.__name__ not in ignored]
 
     if not ignore_stream and not provider.supports_stream and stream:
-        raise StreamNotSupportedError(f'{provider.__name__} does not support "stream" argument')
+        raise StreamNotSupportedError(f'{provider_name} does not support "stream" argument')
 
     if model:
-        debug.log(f'Using {provider.__name__} provider and {model} model')
+        debug.log(f'Using {provider_name} provider and {model} model')
     else:
-        debug.log(f'Using {provider.__name__} provider')
+        debug.log(f'Using {provider_name} provider')
 
     debug.last_provider = provider
     debug.last_model = model
@@ -109,7 +117,7 @@ def get_last_provider(as_dict: bool = False) -> Union[ProviderType, dict[str, st
     if as_dict:
         if last:
             return {
-                "name": last.__name__,
+                "name": last.__name__ if hasattr(last, "__name__") else type(last).__name__,
                 "url": last.url,
                 "model": debug.last_model,
                 "label": getattr(last, "label", None) if hasattr(last, "label") else None
diff --git a/g4f/client/stubs.py b/g4f/client/stubs.py
index 7367ac75d42..cc137b08cf5 100644
--- a/g4f/client/stubs.py
+++ b/g4f/client/stubs.py
@@ -147,4 +147,4 @@ def model_construct(cls, data: List[Image], created: int = None, model: str = No
             model=model,
             provider=provider,
             created=created
-        )
+        )
\ No newline at end of file
diff --git a/g4f/gui/client/static/css/style.css b/g4f/gui/client/static/css/style.css
index 977a8908a21..144de7c31a7 100644
--- a/g4f/gui/client/static/css/style.css
+++ b/g4f/gui/client/static/css/style.css
@@ -477,6 +477,7 @@ body.white .gradient{
     right: 8px;
     top: 8px;
     z-index: 1000;
+    cursor: pointer;
 }
 
 .count_total {
diff --git a/g4f/gui/client/static/js/chat.v1.js b/g4f/gui/client/static/js/chat.v1.js
index 0bf49ac31d5..a1975dd0118 100644
--- a/g4f/gui/client/static/js/chat.v1.js
+++ b/g4f/gui/client/static/js/chat.v1.js
@@ -1327,6 +1327,8 @@ async function on_api() {
 }
 
 async function load_version() {
+    let new_version = document.querySelector(".new_version");
+    if (new_version) return;
     const versions = await api("version");
     document.title = 'g4f - ' + versions["version"];
     let text = "version ~ "
@@ -1334,7 +1336,7 @@ async function load_version() {
         let release_url = 'https://github.com/xtekky/gpt4free/releases/latest';
         let title = `New version: ${versions["latest_version"]}`;
         text += `<a href="${release_url}" target="_blank" title="${title}">${versions["version"]}</a> 🆕`;
-        const new_version = document.createElement("div");
+        new_version = document.createElement("div");
         new_version.classList.add("new_version");
         const link = `<a href="${release_url}" target="_blank" title="${title}">v${versions["latest_version"]}</a>`;
         new_version.innerHTML = `g4f ${link}&nbsp;&nbsp;🆕`;
@@ -1344,6 +1346,7 @@ async function load_version() {
         text += versions["version"];
     }
     document.getElementById("version_text").innerHTML = text
+    setTimeout(load_version, 1000 * 60 * 60); // 1 hour
 }
 setTimeout(load_version, 100);
 
diff --git a/g4f/requests/__init__.py b/g4f/requests/__init__.py
index 2e576d1900b..ded13866308 100644
--- a/g4f/requests/__init__.py
+++ b/g4f/requests/__init__.py
@@ -123,6 +123,7 @@ def get_session_from_browser(url: str, webdriver: WebDriver = None, proxy: str =
         timeout=timeout,
         impersonate="chrome"
     )
+
 def get_cookie_params_from_dict(cookies: Cookies, url: str = None, domain: str = None) -> list[CookieParam]:
     [CookieParam.from_json({
         "name": key,
@@ -172,12 +173,12 @@ def merge_cookies(cookies: Iterator[Morsel], response: Response) -> Cookies:
         cookies = {}
     for cookie in response.cookies.jar:
         cookies[cookie.name] = cookie.value
-        
+
 async def get_nodriver(proxy: str = None, **kwargs)-> Browser:
     if not has_nodriver:
         raise MissingRequirementsError('Install "nodriver" package | pip install -U nodriver')
     user_data_dir = user_config_dir("g4f-nodriver") if has_platformdirs else None
-    debug.log(f"Copilot: Open nodriver with user_dir: {user_data_dir}")
+    debug.log(f"Open nodriver with user_dir: {user_data_dir}")
     return await nodriver.start(
         user_data_dir=user_data_dir,
         browser_args=None if proxy is None else [f"--proxy-server={proxy}"],
diff --git a/g4f/version.py b/g4f/version.py
index 403ce370496..3cde30c7e9f 100644
--- a/g4f/version.py
+++ b/g4f/version.py
@@ -88,7 +88,7 @@ def current_version(self) -> str:
 
         raise VersionNotFoundError("Version not found")
 
-    @cached_property
+    @property
     def latest_version(self) -> str:
         """
         Retrieves the latest version of the 'g4f' package.
diff --git a/requirements-slim.txt b/requirements-slim.txt
index a7e105db282..1ca3bd3e298 100644
--- a/requirements-slim.txt
+++ b/requirements-slim.txt
@@ -3,6 +3,7 @@ pycryptodome
 curl_cffi>=0.6.2
 aiohttp
 certifi
+duckduckgo-search>=6.3.7
 nest_asyncio
 werkzeug
 pillow