The MaxTokens property specifies the maximum number of tokens
the model may generate in response to a request. This value can be
used to limit the length of responses returned by the model.
This property only affects generated output tokens and does not
increase the total context window supported by the selected model.
Increasing the value of this property cannot force a provider or model
to accept larger prompts or additional conversation history beyond the
model's supported limits.
Smaller values can reduce response length, improve response times
and lower token usage costs. However, values that are too small may
cause responses to be truncated or incomplete. If this property is set
to zero, the provider or model default will be used. Some providers
may also impose their own limits on the maximum number of output tokens
that can be generated for a single request.