microsoft/semantic-kernel · critical · ServiceInitializationError

The Anthropic chat model ID is required.

Error message

The Anthropic chat model ID is required.

What it means

After settings are created successfully, the constructor checks that chat_model_id is truthy; if it is empty/None it raises ServiceInitializationError. This is a distinct, later check than the settings ValidationError and points specifically at the model id.

Source

Thrown at python/semantic_kernel/connectors/ai/anthropic/services/anthropic_chat_completion.py:113

            api_key: The optional API key to use. If provided will override,
                the env vars or .env file value.
            async_client: An existing client to use.
            env_file_path: Use the environment settings file as a fallback
                to environment variables.
            env_file_encoding: The encoding of the environment settings file.
        """
        try:
            anthropic_settings = AnthropicSettings(
                api_key=api_key,
                chat_model_id=ai_model_id,
                env_file_path=env_file_path,
                env_file_encoding=env_file_encoding,
            )
        except ValidationError as ex:
            raise ServiceInitializationError("Failed to create Anthropic settings.", ex) from ex

        if not anthropic_settings.chat_model_id:
            raise ServiceInitializationError("The Anthropic chat model ID is required.")

        if not async_client:
            async_client = AsyncAnthropic(
                api_key=anthropic_settings.api_key.get_secret_value(),
            )

        super().__init__(
            async_client=async_client,
            service_id=service_id or anthropic_settings.chat_model_id,
            ai_model_id=anthropic_settings.chat_model_id,
        )

    # region Overriding base class methods

    # Override from AIServiceClientBase
    @override
    def get_prompt_execution_settings_class(self) -> type["PromptExecutionSettings"]:
        return AnthropicChatPromptExecutionSettings

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Pass ai_model_id explicitly (e.g. "claude-3-5-sonnet-latest").
2. Set the model id environment variable AnthropicSettings reads, and confirm it is loaded.
3. Log the resolved chat_model_id during startup to catch empty values early.

Example fix

// before
svc = AnthropicChatCompletion(api_key=key)  # no model id -> error

// after
svc = AnthropicChatCompletion(ai_model_id="claude-3-5-sonnet-latest", api_key=key)

model = ai_model_id or os.environ.get('ANTHROPIC_CHAT_MODEL_ID')
if not model:
    raise ValueError('Anthropic chat model id is required (ai_model_id arg or ANTHROPIC_CHAT_MODEL_ID env)')

def has_anthropic_model_id(ai_model_id: str | None) -> bool:
    return bool(ai_model_id or os.environ.get('ANTHROPIC_CHAT_MODEL_ID'))

try:
    svc = AnthropicChatCompletion(api_key=key)
except ServiceInitializationError as e:
    if 'model ID is required' in str(e):
        svc = AnthropicChatCompletion(ai_model_id='claude-3-5-sonnet-latest', api_key=key)

When it happens

Trigger: Constructing AnthropicChatCompletion with ai_model_id=None and no ANTHROPIC_CHAT_MODEL_ID (or equivalent env var) populated.

Common situations: Forgot the ai_model_id argument; expected the env var to supply it but it is unset/misnamed; passed an empty string.

Related errors

• Failed to create Anthropic settings.
• Failed to create Azure OpenAI settings: {exc}
• Please provide an Azure OpenAI endpoint
• Please provide an Azure OpenAI deployment name
• Tool choice 'none' is not supported by Anthropic.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/6b1a1f03cd6732bc. Report an issue: GitHub.