Prompts and completions.<\/strong><\/h3>\n\n\n\nThe completions endpoint is at the center of our API. It provides a simple interface to our models that is extremely flexible and powerful. You input some text as a prompt<\/strong>, and the model will generate a text completion<\/strong> that attempts to match whatever context or pattern you gave it. For example, if you give the API the prompt, \u201cWrite a tagline for an ice cream shop\u201d, it will return a completion like \u201cWe serve up smiles with every scoop!\u201d<\/p>\n\n\n\nDesigning your prompt is essentially how you \u201cprogram\u201d the model, usually by providing some instructions or a few examples. This is different from most other NLP services which are designed for a single task, such as sentiment classification or named entity recognition. Instead, the completions endpoint can be used for virtually any task including content or code generation, summarization, expansion, conversation, creative writing, style transfer, and more.<\/p>\n\n\n\n
Tokens<\/strong><\/h3>\n\n\n\nOur models understand and process text by breaking it down into tokens. Tokens can be words or just chunks of characters. For example, the word \u201chamburger\u201d gets broken up into the token\u2019s \u201cham\u201d, \u201cbur\u201d and \u201cger\u201d, while a short and common word like \u201cpear\u201d is a single token. Many tokens start with a whitespace, for example \u201chello\u201d and \u201c bye\u201d.<\/p>\n\n\n\n
The number of tokens processed in a given API request depends on the length of both your inputs and outputs. As a rough rule of thumb, 1 token is approximately 4 characters or 0.75 words for English text. One limitation to keep in mind is that your text prompt and generated completion combined must be no more than the model’s maximum context length (for most models this is 2048 tokens, or about 1500 words). Check out our tokenizer tool to learn more about how text translates to tokens.<\/p>\n\n\n\n