Create completion

POSThttps:/api.openai.com/v1/completions

Creates a completion for the provided prompt and parameters.

Request body

  • model
    string

    ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

    • model
      string
      Required
    • model
      string
      Required
      • gpt-3.5-turbo-instruct
        string
      • davinci-002
        string
      • babbage-002
        string
  • prompt
    string or array
    The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note 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.
    • prompt
      string
      Required
      Defaults:
    • prompt
      array
      Required
      • items
        string
        Defaults:
    • prompt
      array
      Required
      • items
        integer
    • prompt
      array
      Required
      • items
        array
        • items
          integer
  • best_of
    integer or null
    Defaults: 1

    Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed.

    When 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.

    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.

  • echo
    boolean or null
    Defaults: false
    Echo back the prompt in addition to the completion
  • frequency_penalty
    number or null
    Defaults: 0

    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.

    See more information about frequency and presence penalties.

  • logit_bias
    object or null
    Defaults: null

    Modify the likelihood of specified tokens appearing in the completion.

    Accepts 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 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.

    As an example, you can pass to prevent the <|endoftext|> token from being generated.

  • logprobs
    integer or null
    Defaults: null

    Include the log probabilities on the logprobs most likely output 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.

    The maximum value for logprobs is 5.

  • max_tokens
    integer or null
    Defaults: 16

    The maximum number of tokens that can be generated in the completion.

    The token count of your prompt plus max_tokens cannot exceed the model's context length. Example Python code for counting tokens.

  • n
    integer or null
    Defaults: 1

    How many completions to generate for each prompt.

    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.

  • presence_penalty
    number or null
    Defaults: 0

    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.

    See more information about frequency and presence penalties.

  • seed
    integer or null

    If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

    Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

  • stop
    string or array

    Not supported with latest reasoning models o3 and o4-mini.

    Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

    • stop
      string or null
      Defaults: <|endoftext|>
    • stop
      array
      • items
        string
  • stream
    boolean or null
    Defaults: false

    Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

  • stream_options
    object or null
    Defaults: null

    Options for streaming response. Only set this when you set stream: true.

    • include_usage
      boolean

      If set, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array.

      All other chunks will also include a usage field, but with a null value. NOTE: If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request.

  • suffix
    string or null
    Defaults: null

    The suffix that comes after a completion of inserted text.

    This parameter is only supported for gpt-3.5-turbo-instruct.

  • temperature
    number or null
    Defaults: 1

    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.

    We generally recommend altering this or top_p but not both.

  • top_p
    number or null
    Defaults: 1

    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.

    We generally recommend altering this or temperature but not both.

  • user
    string

    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Response

Returns a completion object, or a sequence of completion objects if the request is streamed.

Example request
1
curl https://api.openai.com/v1/completions \

2
  -H "Content-Type: application/json" \

3
  -H "Authorization: Bearer $OPENAI_API_KEY" \

4
  -d '{

5
    "model": "VAR_completion_model_id",

6
    "prompt": "Say this is a test",

7
    "max_tokens": 7,

8
    "temperature": 0

9
  }'
Example response
1
{

2
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",

3
  "object": "text_completion",

4
  "created": 1589478378,

5
  "model": "VAR_completion_model_id",

6
  "system_fingerprint": "fp_44709d6fcb",

7
  "choices": [

8
    {

9
      "text": "\n\nThis is indeed a test",

10
      "index": 0,

11
      "logprobs": null,

12
      "finish_reason": "length"

13
    }

14
  ],

15
  "usage": {

16
    "prompt_tokens": 5,

17
    "completion_tokens": 7,

18
    "total_tokens": 12

19
  }

20
}
Built with