Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
supports_tools | bool | True | Whether the model supports tools |
supports_json_schema_output | bool | False | Whether the model supports JSON schema output |
supports_json_object_output | bool | False | Whether the model supports JSON object output |
default_structured_output_mode | StructuredOutputMode | 'tool' | The default structured output mode to use for the model |
prompted_output_template | str | "Always respond with a JSON object that's compatible with this schema:\n\n{schema}\n\nDon't include any text or Markdown fencing before or after.\n" | The instructions template to use for prompted structured output. The '' placeholder will be replaced with the JSON schema for the output. |
json_schema_transformer | type[JsonSchemaTransformer] | None | None | The transformer to use to make JSON schemas for tools and structured output compatible with the model |
thinking_tags | tuple[str, str] | ('<think>', '</think>') | The tags used to indicate thinking parts in the model’s output. Defaults to (' |
ignore_streamed_leading_whitespace | bool | False | Whether to ignore leading whitespace when streaming a response |
openai_supports_tool_choice_required | bool | False | Whether the provider accepts the value tool_choice='required' in the request payload |
Functions
harmony_model_profile
Get the model profile for the OpenAI Harmony Response format.
Parameters:
model_name(str): The name of the model
ModelProfile | None: The model profile for the Harmony model, or None if no specific profile is defined
openai_supports_tool_choice_required set to False, which is then updated with the base OpenAI model profile. This is specifically designed for the OpenAI Harmony format as described in the OpenAI cookbook.