Analyzes images according to specified instructions.

Cancels an "in-progress" batch. The batch will be in status "cancelling" for up to 10 minutes, before changing to "cancelled", where it will have partial results (if any) available in the output file.

Creates and executes a batch of API calls.

Creates a new skill.

Creates a new immutable skill version.

Creates a new vector store and optionally adds files to it, or adds files to an existing vector store.

Deletes an existing conversation.

Deletes an existing model response.

Deletes a skill. This action cannot be undone.

Deletes a skill version. This action cannot be undone.

Deletes a vector store. This action cannot be undone.

Downloads a file from a container.

Downloads a skill as a ZIP file using its ID.

Downloads a skill version as a ZIP file.

Creates an edited or extended image given one or more source images and a prompt.

Generates a chat completion.

Qualifies whether the provided image or text(s) contains violent, hateful, illicit or adult content.

Generates a response.

Transcribes an audio to text.

Translates an audio to English.

Creates an embedding vector representing the input text.

Generates images using GPT Image.

Generates an audio file based on text input and settings.

Retrieves details of the specified batch.

Retrieves an existing model response.

Returns information about a specific skill by its ID.

Returns information about a specific skill version.

Performs an arbitrary authorized API call.

Generates text responses from prompts without requiring an account or connection.

Identifies information in a prompt's text and returns it as structured data.

Updates the default version pointer for a skill.

Uploads a file to be used across the OpenAI platform.