ChatCompletionRequest

Builder for non-streaming chat completion requests.

DSL for building a conversation history.

Builder for streaming chat completion requests.

DSL for building the multimodal content of a single UserMessage.

Sent as frequency_penalty, ignored by the API.

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

The maximum number of tokens that can be generated in the chat completion.

A list of messages comprising the conversation so far.

ID of the model to use.

Sent as presence_penalty, ignored by the API.

How much reasoning the model spends before answering, while thinking mode is on. See ReasoningEffort.

An object specifying the format that the model must output. Setting to { "type": "json_object" } enables JSON Output, which guarantees the message the model generates is valid JSON.

Up to 16 sequences where the API will stop generating further tokens.

If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available, with the stream terminated by a data: [DONE]

Options for streaming response. Only set this when you set stream: true.

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

Switches the model between thinking and non-thinking mode. See Thinking.

Controls which (if any) tool is called by the model.

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

A custom identifier of the end user behind the request, used for content safety review, KVCache isolation, scheduling isolation and privacy management. Must not carry personal data.