All Implemented Interfaces:

com.openai.core.Params
```
public final class CompletionCreateParams
 implements Params
                    
```
Creates a completion for the provided prompt and parameters.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public final class`	`CompletionCreateParams.Body`
`public final class`	`CompletionCreateParams.Builder`	A builder for CompletionCreateParams.
`public final class`	`CompletionCreateParams.Model`	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.
`public final class`	`CompletionCreateParams.Prompt`	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.
`public final class`	`CompletionCreateParams.LogitBias`	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?view=bpe 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.
`public final class`	`CompletionCreateParams.Stop`	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

Field Summary

Fields
Modifier and Type	Field	Description

Constructor Summary

Constructors
Constructor	Description

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`final CompletionCreateParams.Model`	`model()`	ID of the model to use.
`final Optional<CompletionCreateParams.Prompt>`	`prompt()`	The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
`final Optional<Long>`	`bestOf()`	Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token).
`final Optional<Boolean>`	`echo()`	Echo back the prompt in addition to the completion
`final Optional<Double>`	`frequencyPenalty()`	Number between -2.0 and 2.0.
`final Optional<CompletionCreateParams.LogitBias>`	`logitBias()`	Modify the likelihood of specified tokens appearing in the completion.
`final Optional<Long>`	`logprobs()`	Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens.
`final Optional<Long>`	`maxTokens()`	The maximum number of /tokenizer that can be generated in the completion.
`final Optional<Long>`	`n()`	How many completions to generate for each prompt.
`final Optional<Double>`	`presencePenalty()`	Number between -2.0 and 2.0.
`final Optional<Long>`	`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.
`final Optional<CompletionCreateParams.Stop>`	`stop()`	Up to 4 sequences where the API will stop generating further tokens.
`final Optional<ChatCompletionStreamOptions>`	`streamOptions()`	Options for streaming response.
`final Optional<String>`	`suffix()`	The suffix that comes after a completion of inserted text.
`final Optional<Double>`	`temperature()`	What sampling temperature to use, between 0 and 2.
`final Optional<Double>`	`topP()`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
`final Optional<String>`	`user()`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
`final JsonField<CompletionCreateParams.Model>`	`_model()`	ID of the model to use.
`final JsonField<CompletionCreateParams.Prompt>`	`_prompt()`	The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
`final JsonField<Long>`	`_bestOf()`	Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token).
`final JsonField<Boolean>`	`_echo()`	Echo back the prompt in addition to the completion
`final JsonField<Double>`	`_frequencyPenalty()`	Number between -2.0 and 2.0.
`final JsonField<CompletionCreateParams.LogitBias>`	`_logitBias()`	Modify the likelihood of specified tokens appearing in the completion.
`final JsonField<Long>`	`_logprobs()`	Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens.
`final JsonField<Long>`	`_maxTokens()`	The maximum number of /tokenizer that can be generated in the completion.
`final JsonField<Long>`	`_n()`	How many completions to generate for each prompt.
`final JsonField<Double>`	`_presencePenalty()`	Number between -2.0 and 2.0.
`final JsonField<Long>`	`_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.
`final JsonField<CompletionCreateParams.Stop>`	`_stop()`	Up to 4 sequences where the API will stop generating further tokens.
`final JsonField<ChatCompletionStreamOptions>`	`_streamOptions()`	Options for streaming response.
`final JsonField<String>`	`_suffix()`	The suffix that comes after a completion of inserted text.
`final JsonField<Double>`	`_temperature()`	What sampling temperature to use, between 0 and 2.
`final JsonField<Double>`	`_topP()`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
`final JsonField<String>`	`_user()`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
`final Map<String, JsonValue>`	`_additionalBodyProperties()`
`final Headers`	`_additionalHeaders()`
`final QueryParams`	`_additionalQueryParams()`
`Headers`	`_headers()`	The full set of headers in the parameters, including both fixed and additional headers.
`QueryParams`	`_queryParams()`	The full set of query params in the parameters, including both fixed and additional query params.
`final CompletionCreateParams.Builder`	`toBuilder()`
`Boolean`	`equals(Object other)`
`Integer`	`hashCode()`
`String`	`toString()`
`final static CompletionCreateParams.Builder`	`builder()`

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
- Method Detail
  - model
```
 final CompletionCreateParams.Model model()
```
    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
```
 final Optional<CompletionCreateParams.Prompt> prompt()
```
    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.
  - bestOf
```
 final Optional<Long> bestOf()
```
    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
```
 final Optional<Boolean> echo()
```
    Echo back the prompt in addition to the completion
  - frequencyPenalty
```
 final Optional<Double> frequencyPenalty()
```
    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.
  - logitBias
```
 final Optional<CompletionCreateParams.LogitBias> logitBias()
```
    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?view=bpe 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.
  - logprobs
```
 final Optional<Long> 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.
  - maxTokens
```
 final Optional<Long> maxTokens()
```
    The maximum number of /tokenizer 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
```
 final Optional<Long> 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.
  - presencePenalty
```
 final Optional<Double> presencePenalty()
```
    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
```
 final Optional<Long> 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.
  - stop
```
 final Optional<CompletionCreateParams.Stop> stop()
```
    Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
  - streamOptions
```
 final Optional<ChatCompletionStreamOptions> streamOptions()
```
    Options for streaming response. Only set this when you set stream: true.
  - suffix
```
 final Optional<String> suffix()
```
    The suffix that comes after a completion of inserted text.
    This parameter is only supported for gpt-3.5-turbo-instruct.
  - temperature
```
 final Optional<Double> 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.
  - topP
```
 final Optional<Double> topP()
```
    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
```
 final Optional<String> user()
```
    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
  - _model
```
 final JsonField<CompletionCreateParams.Model> _model()
```
    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
```
 final JsonField<CompletionCreateParams.Prompt> _prompt()
```
    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.
  - _bestOf
```
 final JsonField<Long> _bestOf()
```
    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
```
 final JsonField<Boolean> _echo()
```
    Echo back the prompt in addition to the completion
  - _frequencyPenalty
```
 final JsonField<Double> _frequencyPenalty()
```
    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.
  - _logitBias
```
 final JsonField<CompletionCreateParams.LogitBias> _logitBias()
```
    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?view=bpe 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.
  - _logprobs
```
 final JsonField<Long> _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.
  - _maxTokens
```
 final JsonField<Long> _maxTokens()
```
    The maximum number of /tokenizer 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
```
 final JsonField<Long> _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.
  - _presencePenalty
```
 final JsonField<Double> _presencePenalty()
```
    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
```
 final JsonField<Long> _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.
  - _stop
```
 final JsonField<CompletionCreateParams.Stop> _stop()
```
    Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
  - _streamOptions
```
 final JsonField<ChatCompletionStreamOptions> _streamOptions()
```
    Options for streaming response. Only set this when you set stream: true.
  - _suffix
```
 final JsonField<String> _suffix()
```
    The suffix that comes after a completion of inserted text.
    This parameter is only supported for gpt-3.5-turbo-instruct.
  - _temperature
```
 final JsonField<Double> _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.
  - _topP
```
 final JsonField<Double> _topP()
```
    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
```
 final JsonField<String> _user()
```
    A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
  - _additionalBodyProperties
```
 final Map<String, JsonValue> _additionalBodyProperties()
```
  - _additionalHeaders
```
 final Headers _additionalHeaders()
```
  - _additionalQueryParams
```
 final QueryParams _additionalQueryParams()
```
  - _headers
```
 Headers _headers()
```
    The full set of headers in the parameters, including both fixed and additional headers.
  - _queryParams
```
 QueryParams _queryParams()
```
    The full set of query params in the parameters, including both fixed and additional query params.
  - toBuilder
```
 final CompletionCreateParams.Builder toBuilder()
```
  - equals
```
 Boolean equals(Object other)
```
  - hashCode
```
 Integer hashCode()
```
  - toString
```
 String toString()
```
  - builder
```
 final static CompletionCreateParams.Builder builder()
```

Class CompletionCreateParams

Nested Class Summary

Field Summary

Constructor Summary

Enum Constant Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

Method Detail

model

prompt

bestOf

echo

frequencyPenalty

logitBias

logprobs

maxTokens

n

presencePenalty

seed

stop

streamOptions

suffix

temperature

topP

user

_model

_prompt

_bestOf

_echo

_frequencyPenalty

_logitBias

_logprobs

_maxTokens

_n

_presencePenalty

_seed

_stop

_streamOptions

_suffix

_temperature

_topP

_user

_additionalBodyProperties

_additionalHeaders

_additionalQueryParams

_headers

_queryParams

toBuilder

equals

hashCode

toString

builder