Skip to content

Creates a completion for the provided prompt and parameters.

POST
/completions

Authorizations

Request Body required

object
model
required
Any of:
string
prompt
required
One of:
string
""
This is a test.
best_of

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.

integer
default: 1 nullable <= 20
echo

Echo back the prompt in addition to the completion

boolean
nullable
frequency_penalty

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.

number
nullable >= -2 <= 2
logit_bias

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.

object
key
additional properties
integer
logprobs

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.

integer
nullable <= 5
max_tokens

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.

integer
default: 16 nullable
16
n

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.

integer
default: 1 nullable >= 1 <= 128
1
presence_penalty

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.

number
nullable >= -2 <= 2
seed

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.

integer
nullable >= -9223372036854776000 <= 9223372036854776000
stop
One of:
string
default: <|endoftext|> nullable
stream

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.

boolean
nullable
stream_options

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

object
include_usage

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.

boolean
suffix

The suffix that comes after a completion of inserted text.

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

string
nullable
test.
temperature

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.

number
default: 1 nullable <= 2
1
top_p

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.

number
default: 1 nullable <= 1
1
user

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

string
user-1234

Responses

200

OK

Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint).

object
id
required

A unique identifier for the completion.

string
choices
required

The list of completion choices the model generated for the input prompt.

Array<object>
object
finish_reason
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.

string
Allowed values: stop length content_filter
index
required
integer
logprobs
required
object
text_offset
Array<integer>
token_logprobs
Array<number>
tokens
Array<string>
top_logprobs
Array<object>
object
key
additional properties
number
text
required
string
created
required

The Unix timestamp (in seconds) of when the completion was created.

integer
model
required

The model used for completion.

string
system_fingerprint

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.

string
object
required

The object type, which is always “text_completion”

string
Allowed values: text_completion
usage

Usage statistics for the completion request.

object
completion_tokens
required

Number of tokens in the generated completion.

integer
prompt_tokens
required

Number of tokens in the prompt.

integer
total_tokens
required

Total number of tokens used in the request (prompt + completion).

integer
completion_tokens_details

Breakdown of tokens used in a completion.

object
audio_tokens

Audio input tokens generated by the model.

integer
reasoning_tokens

Tokens generated by the model for reasoning.

integer
prompt_tokens_details

Breakdown of tokens used in the prompt.

object
audio_tokens

Audio input tokens present in the prompt.

integer
cached_tokens

Cached tokens present in the prompt.

integer