Creates a completion for the provided prompt and parameters.

POST /completions

Api key auth

application/json

Body Required

model string Required

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.

Any of:
string-1 string string-2 string

Values are gpt-3.5-turbo-instruct, davinci-002, or babbage-002.
prompt string | null | array[string] | array[integer] | array[array] Required

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.

One of:
string-1 string | null array-2 array[string] | null array-3 array[integer] | null array-4 array[array] | null

Default value is empty.

Default value is <|endoftext|>.

At least 1 element. Default value is <|endoftext|>.

At least 1 element. Default value is <|endoftext|>.

At least 1 element.
best_of integer | null

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.

Minimum value is 0, maximum value is 20. Default value is 1.
echo boolean | null

Echo back the prompt in addition to the completion

Default value is false.
frequency_penalty number | null

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.

Minimum value is -2, maximum value is 2. Default value is 0.
logit_bias object | 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 {"50256": -100} to prevent the <|endoftext|> token from being generated.
Hide logit_bias attribute Show logit_bias attribute object | null
- * integer Additional properties
logprobs integer | 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.

Minimum value is 0, maximum value is 5.
max_tokens integer | null

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.

Minimum value is 0. Default value is 16.
n integer | null

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.

Minimum value is 1, maximum value is 128. Default value is 1.
presence_penalty number | null

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.

Minimum value is -2, maximum value is 2. Default value is 0.
seed integer(int64) | 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 | null | array[string]

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

One of:
string-1 string | null array-2 array[string] | null

Default value is <|endoftext|>.

At least 1 but not more than 4 elements.
stream boolean | null

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.

Default value is false.
stream_options object | null

Options for streaming response. Only set this when you set stream: true.
Hide stream_options attribute Show stream_options attribute object | null
- 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 | null

The suffix that comes after a completion of inserted text.

This parameter is only supported for gpt-3.5-turbo-instruct.
temperature number | null

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.

Minimum value is 0, maximum value is 2. Default value is 1.
top_p number | null

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.

Minimum value is 0, maximum value is 1. Default value is 1.
user string

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

Responses

200 application/json

OK
Hide response attributes Show response attributes object
- id string Required
  
  A unique identifier for the completion.
- choices array[object] Required
  
  The list of completion choices the model generated for the input prompt.
  
  Hide choices attributes Show choices attributes object
  
  finish_reason string Required
  
  The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, or content_filter if content was omitted due to a flag from our content filters.
  
  Values are stop, length, or content_filter.
  
  index integer Required
  
  logprobs object | null Required
  
  Hide logprobs attributes Show logprobs attributes object | null
  
  text_offset array[integer]
  
  token_logprobs array[number]
  
  tokens array[string]
  
  top_logprobs array[object]
  
  Hide top_logprobs attribute Show top_logprobs attribute object
  
  * number Additional properties
  
  text string Required
- created integer Required
  
  The Unix timestamp (in seconds) of when the completion was created.
- model string Required
  
  The model used for completion.
- system_fingerprint string
  
  This fingerprint represents the backend configuration that the model runs with.
  
  Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.
- object string Required
  
  The object type, which is always "text_completion"
  
  Value is text_completion.
- usage object
  
  Usage statistics for the completion request.
  
  Hide usage attributes Show usage attributes object
  
  completion_tokens integer Required
  
  Number of tokens in the generated completion.
  
  Default value is 0.
  
  prompt_tokens integer Required
  
  Number of tokens in the prompt.
  
  Default value is 0.
  
  total_tokens integer Required
  
  Total number of tokens used in the request (prompt + completion).
  
  Default value is 0.
  
  completion_tokens_details object
  
  Breakdown of tokens used in a completion.
  
  Hide completion_tokens_details attributes Show completion_tokens_details attributes object
  
  accepted_prediction_tokens integer
  
  When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
  
  Default value is 0.
  
  audio_tokens integer
  
  Audio input tokens generated by the model.
  
  Default value is 0.
  
  reasoning_tokens integer
  
  Tokens generated by the model for reasoning.
  
  Default value is 0.
  
  rejected_prediction_tokens integer
  
  When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits.
  
  Default value is 0.
  
  prompt_tokens_details object
  
  Breakdown of tokens used in the prompt.
  
  Hide prompt_tokens_details attributes Show prompt_tokens_details attributes object
  
  audio_tokens integer
  
  Audio input tokens present in the prompt.
  
  Default value is 0.
  
  cached_tokens integer
  
  Cached tokens present in the prompt.
  
  Default value is 0.

POST /completions

curl \
 --request POST 'https://api.openai.com/v1/completions' \
 --header "Authorization: Bearer $ACCESS_TOKEN" \
 --header "Content-Type: application/json" \
 --data '{"model":"string","prompt":"This is a test.","best_of":1,"echo":false,"frequency_penalty":0,"logit_bias":{"additionalProperty1":42,"additionalProperty2":42},"logprobs":42,"max_tokens":16,"n":1,"presence_penalty":0,"seed":42,"stop":"\u003c|endoftext|\u003e","stream":false,"stream_options":{"include_usage":true},"suffix":"test.","temperature":1,"top_p":1,"user":"user-1234"}'

Request examples

{
  "model": "string",
  "prompt": "This is a test.",
  "best_of": 1,
  "echo": false,
  "frequency_penalty": 0,
  "logit_bias": {
    "additionalProperty1": 42,
    "additionalProperty2": 42
  },
  "logprobs": 42,
  "max_tokens": 16,
  "n": 1,
  "presence_penalty": 0,
  "seed": 42,
  "stop": "<|endoftext|>",
  "stream": false,
  "stream_options": {
    "include_usage": true
  },
  "suffix": "test.",
  "temperature": 1,
  "top_p": 1,
  "user": "user-1234"
}

Response examples (200)

{
  "id": "string",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 42,
      "logprobs": {
        "text_offset": [
          42
        ],
        "token_logprobs": [
          42.0
        ],
        "tokens": [
          "string"
        ],
        "top_logprobs": [
          {
            "additionalProperty1": 42.0,
            "additionalProperty2": 42.0
          }
        ]
      },
      "text": "string"
    }
  ],
  "created": 42,
  "model": "string",
  "system_fingerprint": "string",
  "object": "text_completion",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    }
  }
}

Creates a completion for the provided prompt and parameters.

Body Required

model string Required

prompt string | null | array[string] | array[integer] | array[array] Required

stop string | null | array[string]

Responses