📄️ Completion
Will complete a prompt using a specific model. To obtain a valid model, use `GET` `/models_available`.
📄️ Embeddings
Embeds a text using a specific model. Resulting vectors that can be used for downstream tasks (e.g. semantic similarity) and models (e.g. classifiers). To obtain a valid model, use `GET` `/models_available`.
📄️ Semantic Embeddings
Embeds a prompt using a specific model and semantic embedding method. Resulting vectors that can be used for downstream tasks (e.g. semantic similarity) and models (e.g. classifiers). To obtain a valid model, use `GET` `/models_available`.
📄️ Batched Semantic Embeddings
Embeds multiple prompts using a specific model and semantic embedding method. Resulting vectors that can be used for downstream tasks (e.g. semantic similarity) and models (e.g. classifiers). To obtain a valid model, use `GET` `/models_available`.
📄️ Evaluate
Evaluates the model's likelihood to produce a completion given a prompt.
📄️ Explanation
Better understand the source of a completion, specifically on how much each section of a
📄️ Tokenize
Tokenize a prompt for a specific model. To obtain a valid model, use `GET` `/models_available`.
📄️ Detokenize
Detokenize a list of tokens into a string. To obtain a valid model, use `GET` `/models_available`.
📄️ Q&A
Will answer a question about text given in a prompt.
📄️ Summarize
Will summarize a document using a specific model.
📄️ Query Recent Usage. This interface is deprecated and will be removed in a later version.
A list of the ten most recent tasks successfully completed by the API. Contains statistics