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.
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.
-
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 andn
specifies how many to return –best_of
must be greater thann
.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
andstop
.Minimum value is
0
, maximum value is20
. Default value is1
. -
Echo back the prompt in addition to the completion
Default value is
false
. -
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 is2
. Default value is0
. -
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. -
Include the log probabilities on the
logprobs
most likely output tokens, as well the chosen tokens. For example, iflogprobs
is 5, the API will return a list of the 5 most likely tokens. The API will always return thelogprob
of the sampled token, so there may be up tologprobs+1
elements in the response.The maximum value for
logprobs
is 5.Minimum value is
0
, maximum value is5
. -
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 is16
. -
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
andstop
.Minimum value is
1
, maximum value is128
. Default value is1
. -
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 is2
. Default value is0
. -
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. -
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
. -
Options for streaming response. Only set this when you set
stream: true
. -
The suffix that comes after a completion of inserted text.
This parameter is only supported for
gpt-3.5-turbo-instruct
. -
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 is2
. Default value is1
. -
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 is1
. Default value is1
. -
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
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"}'
{
"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"
}
{
"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
}
}
}