LLMParams

Represents a schema for the structured response.

Used to switch tool calling behavior of LLM

If true, requests the model to add reasoning blocks to the response. Defaults to null. When set to true, responses may include detailed reasoning steps. When false or null, responses are typically shorter and faster.

Maximum number of tokens to generate in the response.

Specifies the number of alternative completions to generate.

Defines the structure for the model's structured response format.

Reserved for speculative proposition of how result would look like, supported only by a number of models, but may greatly improve speed and accuracy of result. For example, in OpenAI that feature is called PredictedOutput

A parameter to control the randomness in the output. Higher values encourage more diverse results, while lower values produce deterministically focused outputs. The value is optional and defaults to null.

Hard cap for reasoning tokens. Ignored by models that don't support budgets. This can be used to limit the amount of tokens used for reasoning when includeThoughts is enabled.

Used to switch tool calling behavior of LLM.

An optional identifier for the user making the request, which can be used for tracking purposes.

Component functions for destructuring declarations

Creates a copy of this instance with the ability to modify any of its properties.

Combines the parameters of the current LLMParams instance with the provided default LLMParams to produce a new instance. Fields that are null in the current instance are replaced by the corresponding fields from the default instance.