The ModelName property returns the name of the current
model. If this property is changed while there is an active
connection, it changes the model associated with the client session.
Subsequent requests will use the new model and the client session does
not need to be disconnected and reconnected.
The specified model name must be supported by the current provider.
When the model name is changed, the internal model flags are reset to
the default flags associated with the new model. If your application
previously changed the model flags by setting the ModelFlags
property, those flags must be set again after changing this property
value.
The control does not attempt to resolve provider-specific aliases.
For example, "gpt-5-mini" and "gpt-5.4-mini"
would be considered different model names even if the provider
considers them equivalent or aliases for the same underlying model.
If you set the value of this property to an empty string, the
ModelName and ModelFlags properties will revert to the
default values for the provider specified by the Provider
property. If the current provider does not define a default model,
this may result in an error indicating that a model name is required.
Changing the model name does not modify or clear the current
message history. However, if conversation history is enabled,
previous prompts and responses may still be included with subsequent
requests sent to the new model. Because different models may interpret
context differently, applications should consider calling
ClearHistory after changing models unless preserving the
existing conversation history is intentional.