diff --git a/docs/user-guide/draft-validation.qmd b/docs/user-guide/draft-validation.qmd
index fccbeffa2..2f8e1b7d3 100644
--- a/docs/user-guide/draft-validation.qmd
+++ b/docs/user-guide/draft-validation.qmd
@@ -66,7 +66,7 @@ data = pb.load_dataset(dataset="global_sales", tbl_type="polars")
 # Generate a validation plan
 pb.DraftValidation(
     data=data,
-    model="anthropic:claude-3-7-sonnet-latest",
+    model="anthropic:claude-sonnet-4-5",
     api_key="your_api_key_here"  # Replace with your actual API key
 )
 ```
@@ -159,7 +159,7 @@ api_key = os.getenv("ANTHROPIC_API_KEY")
 
 draft_validation = pb.DraftValidation(
     data=data,
-    model="anthropic:claude-3-7-sonnet-latest",
+    model="anthropic:claude-sonnet-4-5",
     api_key=api_key
 )
 ```
@@ -179,7 +179,7 @@ If your API keys have standard names (like `ANTHROPIC_API_KEY` or `OPENAI_API_KE
 # No API key needed if stored in .env with standard names
 draft_validation = pb.DraftValidation(
     data=data,
-    model="anthropic:claude-3-7-sonnet-latest"
+    model="anthropic:claude-sonnet-4-5"
 )
 ```
 
@@ -191,7 +191,7 @@ Here's an example of a validation plan that might be generated by `DraftValidati
 ```python
 pb.DraftValidation(
     pb.load_dataset(dataset="nycflights", tbl_type="duckdb",
-    model="anthropic:claude-3-7-sonnet-latest"
+    model="anthropic:claude-sonnet-4-5"
 )
 ```
 
@@ -269,7 +269,7 @@ When using `DraftValidation`, you specify the model in the format `"provider:mod
 
 ```python
 # Using Anthropic's Claude model
-pb.DraftValidation(data=data, model="anthropic:claude-3-7-sonnet-latest")
+pb.DraftValidation(data=data, model="anthropic:claude-sonnet-4-5")
 
 # Using OpenAI's GPT model
 pb.DraftValidation(data=data, model="openai:gpt-4-turbo")
@@ -285,7 +285,7 @@ pb.DraftValidation(data=data, model="bedrock:anthropic.claude-3-sonnet-20240229-
 
 Different models have different capabilities when it comes to generating validation plans:
 
-- Anthropic Claude 3.7 Sonnet generally provides the most comprehensive and accurate validation
+- Anthropic Claude Sonnet 4.5 generally provides the most comprehensive and accurate validation
 plans
 - OpenAI GPT-4 models also perform well
 - Local models through Ollama can be useful for private data but they currently have reduced
diff --git a/pointblank/_interrogation.py b/pointblank/_interrogation.py
index 1ceff1f55..09d9d8333 100644
--- a/pointblank/_interrogation.py
+++ b/pointblank/_interrogation.py
@@ -1895,6 +1895,7 @@ def interrogate_prompt(tbl: FrameT, columns_subset: list[str] | None, ai_config:
             provider=llm_provider,
             model=llm_model,
             api_key=None,  # Will be loaded from environment variables
+            verify_ssl=True,  # Default to verifying SSL certificates
         )
 
         # Set up batch configuration
diff --git a/pointblank/_utils_ai.py b/pointblank/_utils_ai.py
index 05a22e240..a94c87939 100644
--- a/pointblank/_utils_ai.py
+++ b/pointblank/_utils_ai.py
@@ -28,17 +28,22 @@ class _LLMConfig:
     provider
         LLM provider name (e.g., 'anthropic', 'openai', 'ollama', 'bedrock').
     model
-        Model name (e.g., 'claude-3-sonnet-20240229', 'gpt-4').
+        Model name (e.g., 'claude-sonnet-4-5', 'gpt-4').
     api_key
         API key for the provider. If None, will be read from environment.
+    verify_ssl
+        Whether to verify SSL certificates when making requests. Defaults to True.
     """
 
     provider: str
     model: str
     api_key: Optional[str] = None
+    verify_ssl: bool = True
 
 
-def _create_chat_instance(provider: str, model_name: str, api_key: Optional[str] = None):
+def _create_chat_instance(
+    provider: str, model_name: str, api_key: Optional[str] = None, verify_ssl: bool = True
+):
     """
     Create a chatlas chat instance for the specified provider.
 
@@ -50,6 +55,8 @@ def _create_chat_instance(provider: str, model_name: str, api_key: Optional[str]
         The model name for the provider.
     api_key
         Optional API key. If None, will be read from environment.
+    verify_ssl
+        Whether to verify SSL certificates when making requests. Defaults to True.
 
     Returns
     -------
@@ -89,6 +96,17 @@ def _create_chat_instance(provider: str, model_name: str, api_key: Optional[str]
   {"index": 2, "result": true}
 ]"""
 
+    # Create httpx client with SSL verification settings
+    try:
+        import httpx  # noqa
+    except ImportError:  # pragma: no cover
+        raise ImportError(  # pragma: no cover
+            "The `httpx` package is required for SSL configuration. "
+            "Please install it using `pip install httpx`."
+        )
+
+    http_client = httpx.AsyncClient(verify=verify_ssl)
+
     # Create provider-specific chat instance
     if provider == "anthropic":  # pragma: no cover
         # Check that the anthropic package is installed
@@ -106,6 +124,7 @@ def _create_chat_instance(provider: str, model_name: str, api_key: Optional[str]
             model=model_name,
             api_key=api_key,
             system_prompt=system_prompt,
+            kwargs={"http_client": http_client},
         )
 
     elif provider == "openai":  # pragma: no cover
@@ -124,6 +143,7 @@ def _create_chat_instance(provider: str, model_name: str, api_key: Optional[str]
             model=model_name,
             api_key=api_key,
             system_prompt=system_prompt,
+            kwargs={"http_client": http_client},
         )
 
     elif provider == "ollama":  # pragma: no cover
@@ -141,6 +161,7 @@ def _create_chat_instance(provider: str, model_name: str, api_key: Optional[str]
         chat = ChatOllama(
             model=model_name,
             system_prompt=system_prompt,
+            kwargs={"http_client": http_client},
         )
 
     elif provider == "bedrock":  # pragma: no cover
@@ -149,6 +170,7 @@ def _create_chat_instance(provider: str, model_name: str, api_key: Optional[str]
         chat = ChatBedrockAnthropic(
             model=model_name,
             system_prompt=system_prompt,
+            kwargs={"http_client": http_client},
         )
 
     else:
@@ -722,7 +744,10 @@ def __init__(self, llm_config: _LLMConfig):
         """
         self.llm_config = llm_config
         self.chat = _create_chat_instance(
-            provider=llm_config.provider, model_name=llm_config.model, api_key=llm_config.api_key
+            provider=llm_config.provider,
+            model_name=llm_config.model,
+            api_key=llm_config.api_key,
+            verify_ssl=llm_config.verify_ssl,
         )
 
     def validate_batches(
diff --git a/pointblank/assistant.py b/pointblank/assistant.py
index 21a8eee85..52eae95f0 100644
--- a/pointblank/assistant.py
+++ b/pointblank/assistant.py
@@ -55,7 +55,7 @@ def assistant(
     ----------
     model
         The model to be used. This should be in the form of `provider:model` (e.g.,
-        `"anthropic:claude-3-5-sonnet-latest"`). Supported providers are `"anthropic"`, `"openai"`,
+        `"anthropic:claude-sonnet-4-5"`). Supported providers are `"anthropic"`, `"openai"`,
         `"ollama"`, and `"bedrock"`.
     data
         An optional data table to focus on during discussion with the PbA, which could be a
diff --git a/pointblank/data/api-docs.txt b/pointblank/data/api-docs.txt
index d3f3e5e70..fb57594e7 100644
--- a/pointblank/data/api-docs.txt
+++ b/pointblank/data/api-docs.txt
@@ -1157,7 +1157,7 @@ Definition of a schema object.
     `Schema` object is used in a validation workflow.
     
 
-DraftValidation(data: 'FrameT | Any', model: 'str', api_key: 'str | None' = None) -> None
+DraftValidation(data: 'FrameT | Any', model: 'str', api_key: 'str | None' = None, verify_ssl: 'bool' = True) -> None
 
     Draft a validation plan for a given table using an LLM.
 
@@ -1180,10 +1180,15 @@ DraftValidation(data: 'FrameT | Any', model: 'str', api_key: 'str | None' = None
         The data to be used for drafting a validation plan.
     model
         The model to be used. This should be in the form of `provider:model` (e.g.,
-        `"anthropic:claude-3-5-sonnet-latest"`). Supported providers are `"anthropic"`, `"openai"`,
+        `"anthropic:claude-sonnet-4-5"`). Supported providers are `"anthropic"`, `"openai"`,
         `"ollama"`, and `"bedrock"`.
     api_key
         The API key to be used for the model.
+    verify_ssl
+        Whether to verify SSL certificates when making requests to the LLM provider. Set to `False`
+        to disable SSL verification (e.g., when behind a corporate firewall with self-signed
+        certificates). Defaults to `True`. Use with caution as disabling SSL verification can pose
+        security risks.
 
     Returns
     -------
@@ -1225,6 +1230,33 @@ DraftValidation(data: 'FrameT | Any', model: 'str', api_key: 'str | None' = None
     There's no need to have the `python-dotenv` package installed when using `.env` files in this
     way.
 
+    Notes on SSL Certificate Verification
+    --------------------------------------
+    By default, SSL certificate verification is enabled for all requests to LLM providers. However,
+    in certain network environments (such as corporate networks with self-signed certificates or
+    firewall proxies), you may encounter SSL certificate verification errors.
+
+    To disable SSL verification, set the `verify_ssl` parameter to `False`:
+
+    ```python
+    import pointblank as pb
+
+    data = pb.load_dataset(dataset="nycflights", tbl_type="duckdb")
+
+    # Disable SSL verification for networks with self-signed certificates
+    pb.DraftValidation(
+        data=data,
+        model="anthropic:claude-sonnet-4-5",
+        verify_ssl=False
+    )
+    ```
+
+    :::{.callout-warning}
+    Disabling SSL verification (through `verify_ssl=False`) can expose your API keys and data to
+    man-in-the-middle attacks. Only use this option in trusted network environments and when
+    absolutely necessary.
+    :::
+
     Notes on Data Sent to the Model Provider
     ----------------------------------------
     The data sent to the model provider is a JSON summary of the table. This data summary is
@@ -1251,7 +1283,7 @@ DraftValidation(data: 'FrameT | Any', model: 'str', api_key: 'str | None' = None
     Let's look at how the `DraftValidation` class can be used to draft a validation plan for a
     table. The table to be used is `"nycflights"`, which is available here via the
     [`load_dataset()`](`pointblank.load_dataset`) function. The model to be used is
-    `"anthropic:claude-3-5-sonnet-latest"` (which performs very well compared to other LLMs). The
+    `"anthropic:claude-sonnet-4-5"` (which performs very well compared to other LLMs). The
     example assumes that the API key is stored in an `.env` file as `ANTHROPIC_API_KEY`.
 
     ```python
@@ -1261,7 +1293,7 @@ DraftValidation(data: 'FrameT | Any', model: 'str', api_key: 'str | None' = None
     data = pb.load_dataset(dataset="nycflights", tbl_type="duckdb")
 
     # Draft a validation plan for the "nycflights" table
-    pb.DraftValidation(data=data, model="anthropic:claude-3-5-sonnet-latest")
+    pb.DraftValidation(data=data, model="anthropic:claude-sonnet-4-5")
     ```
 
     The output will be a drafted validation plan for the `"nycflights"` table and this will appear
@@ -5853,10 +5885,10 @@ prompt(self, prompt: 'str', model: 'str', columns_subset: 'str | list[str] | Non
             so try to include only the columns necessary for the validation.
         model
             The model to be used. This should be in the form of `provider:model` (e.g.,
-            `"anthropic:claude-3-5-sonnet-latest"`). Supported providers are `"anthropic"`,
-            `"openai"`, `"ollama"`, and `"bedrock"`. The model name should be the specific model to
-            be used from the provider. Model names are subject to change so consult the provider's
-            documentation for the most up-to-date model names.
+            `"anthropic:claude-sonnet-4-5"`). Supported providers are `"anthropic"`, `"openai"`,
+            `"ollama"`, and `"bedrock"`. The model name should be the specific model to be used from
+            the provider. Model names are subject to change so consult the provider's documentation
+            for the most up-to-date model names.
         batch_size
             Number of rows to process in each batch. Larger batches are more efficient but may hit
             API limits. Default is `1000`.
@@ -9927,7 +9959,7 @@ assistant(model: 'str', data: 'FrameT | Any | None' = None, tbl_name: 'str | Non
     ----------
     model
         The model to be used. This should be in the form of `provider:model` (e.g.,
-        `"anthropic:claude-3-5-sonnet-latest"`). Supported providers are `"anthropic"`, `"openai"`,
+        `"anthropic:claude-sonnet-4-5"`). Supported providers are `"anthropic"`, `"openai"`,
         `"ollama"`, and `"bedrock"`.
     data
         An optional data table to focus on during discussion with the PbA, which could be a
diff --git a/pointblank/draft.py b/pointblank/draft.py
index c69b37ab8..8531befda 100644
--- a/pointblank/draft.py
+++ b/pointblank/draft.py
@@ -38,10 +38,15 @@ class DraftValidation:
         The data to be used for drafting a validation plan.
     model
         The model to be used. This should be in the form of `provider:model` (e.g.,
-        `"anthropic:claude-3-5-sonnet-latest"`). Supported providers are `"anthropic"`, `"openai"`,
+        `"anthropic:claude-sonnet-4-5"`). Supported providers are `"anthropic"`, `"openai"`,
         `"ollama"`, and `"bedrock"`.
     api_key
         The API key to be used for the model.
+    verify_ssl
+        Whether to verify SSL certificates when making requests to the LLM provider. Set to `False`
+        to disable SSL verification (e.g., when behind a corporate firewall with self-signed
+        certificates). Defaults to `True`. Use with caution as disabling SSL verification can pose
+        security risks.
 
     Returns
     -------
@@ -83,6 +88,33 @@ class DraftValidation:
     There's no need to have the `python-dotenv` package installed when using `.env` files in this
     way.
 
+    Notes on SSL Certificate Verification
+    --------------------------------------
+    By default, SSL certificate verification is enabled for all requests to LLM providers. However,
+    in certain network environments (such as corporate networks with self-signed certificates or
+    firewall proxies), you may encounter SSL certificate verification errors.
+
+    To disable SSL verification, set the `verify_ssl` parameter to `False`:
+
+    ```python
+    import pointblank as pb
+
+    data = pb.load_dataset(dataset="nycflights", tbl_type="duckdb")
+
+    # Disable SSL verification for networks with self-signed certificates
+    pb.DraftValidation(
+        data=data,
+        model="anthropic:claude-sonnet-4-5",
+        verify_ssl=False
+    )
+    ```
+
+    :::{.callout-warning}
+    Disabling SSL verification (through `verify_ssl=False`) can expose your API keys and data to
+    man-in-the-middle attacks. Only use this option in trusted network environments and when
+    absolutely necessary.
+    :::
+
     Notes on Data Sent to the Model Provider
     ----------------------------------------
     The data sent to the model provider is a JSON summary of the table. This data summary is
@@ -109,7 +141,7 @@ class DraftValidation:
     Let's look at how the `DraftValidation` class can be used to draft a validation plan for a
     table. The table to be used is `"nycflights"`, which is available here via the
     [`load_dataset()`](`pointblank.load_dataset`) function. The model to be used is
-    `"anthropic:claude-3-5-sonnet-latest"` (which performs very well compared to other LLMs). The
+    `"anthropic:claude-sonnet-4-5"` (which performs very well compared to other LLMs). The
     example assumes that the API key is stored in an `.env` file as `ANTHROPIC_API_KEY`.
 
     ```python
@@ -119,7 +151,7 @@ class DraftValidation:
     data = pb.load_dataset(dataset="nycflights", tbl_type="duckdb")
 
     # Draft a validation plan for the "nycflights" table
-    pb.DraftValidation(data=data, model="anthropic:claude-3-5-sonnet-latest")
+    pb.DraftValidation(data=data, model="anthropic:claude-sonnet-4-5")
     ```
 
     The output will be a drafted validation plan for the `"nycflights"` table and this will appear
@@ -194,6 +226,7 @@ class DraftValidation:
     data: FrameT | Any
     model: str
     api_key: str | None = None
+    verify_ssl: bool = True
     response: str = field(init=False)
 
     def __post_init__(self):
@@ -280,6 +313,18 @@ def __post_init__(self):
             "    per line)"
         )
 
+        # Create httpx client with SSL verification settings
+        # This will be passed to the LLM provider's chat client
+        try:
+            import httpx  # noqa
+        except ImportError:  # pragma: no cover
+            raise ImportError(  # pragma: no cover
+                "The `httpx` package is required for SSL configuration. "
+                "Please install it using `pip install httpx`."
+            )
+
+        http_client = httpx.AsyncClient(verify=self.verify_ssl)
+
         if provider == "anthropic":  # pragma: no cover
             # Check that the anthropic package is installed
             try:
@@ -296,6 +341,7 @@ def __post_init__(self):
                 model=model_name,
                 system_prompt="You are a terse assistant and a Python expert.",
                 api_key=self.api_key,
+                kwargs={"http_client": http_client},
             )
 
         if provider == "openai":  # pragma: no cover
@@ -314,6 +360,7 @@ def __post_init__(self):
                 model=model_name,
                 system_prompt="You are a terse assistant and a Python expert.",
                 api_key=self.api_key,
+                kwargs={"http_client": http_client},
             )
 
         if provider == "ollama":  # pragma: no cover
@@ -331,6 +378,7 @@ def __post_init__(self):
             chat = ChatOllama(  # pragma: no cover
                 model=model_name,
                 system_prompt="You are a terse assistant and a Python expert.",
+                kwargs={"http_client": http_client},
             )
 
         if provider == "bedrock":  # pragma: no cover
@@ -339,6 +387,7 @@ def __post_init__(self):
             chat = ChatBedrockAnthropic(  # pragma: no cover
                 model=model_name,
                 system_prompt="You are a terse assistant and a Python expert.",
+                kwargs={"http_client": http_client},
             )
 
         self.response = str(chat.chat(prompt, stream=False, echo="none"))  # pragma: no cover
diff --git a/pointblank/validate.py b/pointblank/validate.py
index 8843e73e3..5e0343803 100644
--- a/pointblank/validate.py
+++ b/pointblank/validate.py
@@ -9396,10 +9396,10 @@ def prompt(
             so try to include only the columns necessary for the validation.
         model
             The model to be used. This should be in the form of `provider:model` (e.g.,
-            `"anthropic:claude-3-5-sonnet-latest"`). Supported providers are `"anthropic"`,
-            `"openai"`, `"ollama"`, and `"bedrock"`. The model name should be the specific model to
-            be used from the provider. Model names are subject to change so consult the provider's
-            documentation for the most up-to-date model names.
+            `"anthropic:claude-sonnet-4-5"`). Supported providers are `"anthropic"`, `"openai"`,
+            `"ollama"`, and `"bedrock"`. The model name should be the specific model to be used from
+            the provider. Model names are subject to change so consult the provider's documentation
+            for the most up-to-date model names.
         batch_size
             Number of rows to process in each batch. Larger batches are more efficient but may hit
             API limits. Default is `1000`.
diff --git a/pointblank_mcp_server/pointblank_server.py b/pointblank_mcp_server/pointblank_server.py
index 1bda07b7e..5be708726 100644
--- a/pointblank_mcp_server/pointblank_server.py
+++ b/pointblank_mcp_server/pointblank_server.py
@@ -2429,8 +2429,8 @@ async def draft_validation_plan(
     dataframe_id: Annotated[str, "ID of the DataFrame to generate validation plan for."],
     model: Annotated[
         str,
-        "AI model to use in format 'provider:model' (e.g., 'anthropic:claude-3-5-sonnet-latest', 'openai:gpt-4'). Supported providers: anthropic, openai, ollama, bedrock.",
-    ] = "anthropic:claude-3-5-sonnet-latest",
+        "AI model to use in format 'provider:model' (e.g., 'anthropic:claude-sonnet-4-5', 'openai:gpt-4'). Supported providers: anthropic, openai, ollama, bedrock.",
+    ] = "anthropic:claude-sonnet-4-5",
     api_key: Annotated[
         Optional[str],
         "API key for the model provider. If not provided, will try to load from environment variables or .env file.",
diff --git a/pyproject.toml b/pyproject.toml
index 5370945ad..3b2850fa6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -55,6 +55,7 @@ generate = [
     "chatlas>=0.3.0",
     "anthropic[bedrock]>=0.45.2",
     "openai>=1.63.0",
+    "httpx>=0.28.0",
     "shiny>=1.3.0",
 ]
 mcp = [
diff --git a/tests/test__utils_ai.py b/tests/test__utils_ai.py
index 81dcc7b21..c394529cc 100644
--- a/tests/test__utils_ai.py
+++ b/tests/test__utils_ai.py
@@ -50,7 +50,7 @@ def sample_pl_data():
 @pytest.fixture
 def llm_config():
     """Sample LLM configuration."""
-    return _LLMConfig(provider="anthropic", model="claude-3-sonnet-20240229", api_key="test-key")
+    return _LLMConfig(provider="anthropic", model="claude-sonnet-4-5", api_key="test-key")
 
 
 @pytest.fixture
@@ -84,10 +84,10 @@ def test_llm_config_creation():
 
 def test_llm_config_with_api_key():
     """Test LLMConfig with API key."""
-    config = _LLMConfig(provider="anthropic", model="claude-3", api_key="test-key")
+    config = _LLMConfig(provider="anthropic", model="claude-sonnet-4-5", api_key="test-key")
 
     assert config.provider == "anthropic"
-    assert config.model == "claude-3"
+    assert config.model == "claude-sonnet-4-5"
     assert config.api_key == "test-key"
 
 
@@ -529,7 +529,10 @@ def test_ai_validation_engine_init(mock_create_chat, llm_config):
     assert engine.llm_config is llm_config
     assert engine.chat is mock_chat
     mock_create_chat.assert_called_once_with(
-        provider="anthropic", model_name="claude-3-sonnet-20240229", api_key="test-key"
+        provider="anthropic",
+        model_name="claude-sonnet-4-5",
+        api_key="test-key",
+        verify_ssl=True,
     )
 
 
@@ -709,7 +712,10 @@ def mock_chat_response(prompt, **kwargs):
         mock_create_chat.return_value = mock_chat
 
         # Setup components
-        llm_config = _LLMConfig(provider="anthropic", model="claude-3")
+        llm_config = _LLMConfig(
+            provider="anthropic",
+            model="claude-sonnet-4-5",
+        )
         batch_config = _BatchConfig(size=2, max_concurrent=1)
 
         # Create batcher and batches