AI/ML API

The content to classify for safety. For text, provide the raw string. For images, provide a URL or base64-encoded data URI.

ID of the content moderation model to use. Choose any model from the documentation: https://docs.aimlapi.com/api-references/moderation-safety-models#all-available-content-moderation-models

Data from the action execution

Error if any occurred during the execution of the action

Whether or not the action execution was successful or not

Number of completions to generate for each prompt.

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

Unique identifier representing the end-user.

The identifier of the model to use for generating responses.

Nucleus sampling threshold; model considers tokens with cumulative probability up to top_p.

Whether to stream the response as tokens are generated.

List of message objects for conversation history.

Adjust the likelihood of specified tokens appearing in the completion.

Maximum number of tokens to generate in the response.

Sampling temperature between 0 and 1; higher values make output more random.

Penalty for new tokens based on whether they appear in the text so far.

Penalty for new tokens based on their existing frequency in the text.

Data from the action execution

Error if any occurred during the execution of the action

Whether or not the action execution was successful or not