OpenAI

Create embeddings - Creates an embedding vector representing the input text

User - A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Encoding format - Choose the format to return the embeddings in. Can be either float or base64. Defaults to float.

Model - Choose the model to use

Input - Enter the input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays.

Dimensions - The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.

Create a chat completion - Creates a model response for the given chat conversation

User - A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse

Model - Choose the model to use

Tool choice - Controls which (if any) function is called by the model

Messages - Enter a list of messages comprising the conversation so far

See Create a chat completion - Messages.

Amount of completions - Enter how many completions to generate for each prompt

Stop sequences - Enter up to 4 stop sequences as comma-separated values. The returned text won`t contain the stop sequence.

Temperature - Enter what sampling temperature to use

Maximum tokens - The maximum number of tokens to generate in the completion

Seed - This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

Create a chat completion (advanced) - Creates a model response for the given chat conversation

User - A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse

Model - Choose the model to use

Tool choice - Controls which (if any) function is called by the model

Messages - Enter a list of messages comprising the conversation so far

Amount of completions - Enter how many completions to generate for each prompt

Stop sequences - Enter up to 4 stop sequences as comma-separated values. The returned text won`t contain the stop sequence.

Temperature - Enter what sampling temperature to use

Maximum tokens - The maximum number of tokens to generate in the completion

Seed - This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

Create moderations - Classifies if text is potentially harmful

Model - Choose the model to use. Two content moderations models are available: text-moderation-stable and text-moderation-latest. Defaults to text-moderation-latest.

Input - Enter the input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays.

Create a completion - Creates a completion for the provided prompt and parameters

Model - Choose the model to use

Amount of completions - Enter how many completions to generate for each prompt

Stop sequences - Enter up to 4 stop sequences as comma-separated values. The returned text won`t contain the stop sequence.

Temperature - Enter what sampling temperature to use

Prompt - Provide the prompt to generate completions for

Maximum tokens - The maximum number of tokens to generate in the completion

Create an edit - Creates a new edit for the provided input, instruction, and parameters

Model - Choose the model to use

Amount of edits - Enter how many edits to generate for the input and instruction

Input - Enter the input text to use as a starting point for the edit

Instruction - Enter the instruction that tells the model how to edit the prompt

Temperature - Enter what sampling temperature to use