Create a new client.

Parameters for audio output.

Parameters for speech output.

Embeddings: The number of dimensions the resulting output embeddings should have.

Disable parallel tool calling.

Tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100.

Whether to return log probabilities of the output tokens or not.

Key-value pair that can be attached to an object.

Output types that you would like the model to generate for this request.

Parameters for image output.

Constrains effort on reasoning for reasoning models.

Specifies the latency tier to use for processing the request.

Parameters for image output.

Whether or not to store the output of this chat completion request for use in model distillation or evals products.

Enable streaming and include usage information in the streaming response.

Parameters for image output.

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.

Completion Variation.

Embedding is a single vector.

Embeddings is the metadata for a generated embedding vector.

Message with text or object content.

Metrics.

Completion Response.

Completion choices.

text content.

text content.

A set of tool calls.