Optionalfrequency_OptionalfunctionsOptionalmax_The maximum number of tokens to generate in the response.
An array of message objects representing the conversation history.
The content of the message as a string.
The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool').
Optionalpresence_Increases the likelihood of the model introducing new topics.
OptionalrawIf true, a chat template is not applied and you must adhere to the specific model's expected formatting.
Optionalrepetition_Penalty for repeated tokens; higher values discourage repetition.
Optionalresponse_OptionalseedRandom seed for reproducibility of the generation.
OptionalstreamIf true, the response will be streamed back incrementally using SSE, Server Sent Events.
OptionaltemperatureControls the randomness of the output; higher values produce more random results.
OptionaltoolsA list of tools available for the assistant to use.
A brief description of what the tool does.
The name of the tool. More descriptive the better.
Schema defining the parameters accepted by the tool.
Definitions of each parameter.
Optionalrequired?: string[]List of required parameter names.
The type of the parameters object (usually 'object').
Details of the function tool.
A brief description of what the function does.
The name of the function.
Schema defining the parameters accepted by the function.
Definitions of each parameter.
Optionalrequired?: string[]List of required parameter names.
The type of the parameters object (usually 'object').
Specifies the type of tool (e.g., 'function').
Optionaltop_Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises.
Optionaltop_Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses.
Decreases the likelihood of the model repeating the same lines verbatim.