Creates a completion for the provided prompt and parameters

{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "best_of": {
      "type": "integer",
      "description": "Generates `best_of` completions server-side and returns the \"best\" (the one with the highest log probability per token). Results cannot be streamed.\n\nWhen used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`.\n\n**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.\n"
    },
    "echo": {
      "type": "boolean",
      "description": "Echo back the prompt in addition to the completion\n"
    },
    "frequency_penalty": {
      "type": "number",
      "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.\n\n[See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)\n"
    },
    "logit_bias": {
      "type": "object",
      "description": "Modify the likelihood of specified tokens appearing in the completion.\n\nAccepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.\n\nAs an example, you can pass `{\"50256\": -100}` to prevent the <|endoftext|> token from being generated.\n"
    },
    "logprobs": {
      "type": "integer",
      "description": "Include the log probabilities on the `logprobs` most likely tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.\n\nThe maximum value for `logprobs` is 5. If you need more than this, please contact us through our [Help center](https://help.openai.com) and describe your use case.\n"
    },
    "max_tokens": {
      "type": "integer",
      "description": "The maximum number of [tokens](/tokenizer) to generate in the completion.\n\nThe token count of your prompt plus `max_tokens` cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).\n"
    },
    "model": {
      "type": "string",
      "description": "ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them."
    },
    "n": {
      "type": "integer",
      "description": "How many completions to generate for each prompt.\n\n**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.\n"
    },
    "presence_penalty": {
      "type": "number",
      "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.\n\n[See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)\n"
    },
    "prompt": {
      "description": "The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.\n\nNote that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.\n",
      "type": "object"
    },
    "stop": {
      "description": "Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.\n",
      "type": "object"
    },
    "stream": {
      "type": "boolean",
      "description": "Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message.\n"
    },
    "suffix": {
      "type": "string",
      "description": "The suffix that comes after a completion of inserted text."
    },
    "temperature": {
      "type": "number",
      "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n\nWe generally recommend altering this or `top_p` but not both.\n"
    },
    "top_p": {
      "type": "number",
      "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or `temperature` but not both.\n"
    },
    "user": {
      "type": "string",
      "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\n"
    }
  }
}