API Reference

Completions

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create completion

client.Completions.New(ctx, body) (*Completion, error)

POST/completions

Creates a completion for the provided prompt and parameters.

ParametersExpand Collapse

body CompletionNewParams

Model param.Field[CompletionNewParamsModel]

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.

string

CompletionNewParamsModel

Accepts one of the following:

const CompletionNewParamsModelGPT3_5TurboInstruct CompletionNewParamsModel = "gpt-3.5-turbo-instruct"

const CompletionNewParamsModelDavinci002 CompletionNewParamsModel = "davinci-002"

const CompletionNewParamsModelBabbage002 CompletionNewParamsModel = "babbage-002"

Prompt param.Field[CompletionNewParamsPromptUnion]

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.

string

[]string

[]int64

[][]int64

BestOf param.Field[int64]optional

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.

minimum0

maximum20

Echo param.Field[bool]optional

Echo back the prompt in addition to the completion

FrequencyPenalty param.Field[float64]optional

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-2

maximum2

LogitBias param.Field[map[string, int64]]optional

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.

Logprobs param.Field[int64]optional

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.

minimum0

maximum5

MaxTokens param.Field[int64]optional

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.

minimum0

N param.Field[int64]optional

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.

minimum1

maximum128

PresencePenalty param.Field[float64]optional

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-2

maximum2

Seed param.Field[int64]optional

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.

formatint64

Stop param.Field[CompletionNewParamsStopUnion]optional

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.

string

[]string

StreamOptions param.Field[ChatCompletionStreamOptions]optional

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

Suffix param.Field[string]optional

The suffix that comes after a completion of inserted text.

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

Temperature param.Field[float64]optional

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.

minimum0

maximum2

TopP param.Field[float64]optional

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.

minimum0

maximum1

User param.Field[string]optional

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

ReturnsExpand Collapse

type Completion struct{…}

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

ID string

A unique identifier for the completion.

Choices []CompletionChoice

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

FinishReason CompletionChoiceFinishReason

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.

Accepts one of the following:

const CompletionChoiceFinishReasonStop CompletionChoiceFinishReason = "stop"

const CompletionChoiceFinishReasonLength CompletionChoiceFinishReason = "length"

const CompletionChoiceFinishReasonContentFilter CompletionChoiceFinishReason = "content_filter"

Index int64

Logprobs CompletionChoiceLogprobs

TextOffset []int64optional

TokenLogprobs []float64optional

Tokens []stringoptional

TopLogprobs []map[string, float64]optional

Text string

Created int64

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

Model string

The model used for completion.

Object TextCompletion

The object type, which is always "text_completion"

SystemFingerprint stringoptional

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.

Usage CompletionUsageoptional

Usage statistics for the completion request.

CompletionTokens int64

Number of tokens in the generated completion.

PromptTokens int64

Number of tokens in the prompt.

TotalTokens int64

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

CompletionTokensDetails CompletionUsageCompletionTokensDetailsoptional

Breakdown of tokens used in a completion.

AcceptedPredictionTokens int64optional

When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.

AudioTokens int64optional

Audio input tokens generated by the model.

ReasoningTokens int64optional

Tokens generated by the model for reasoning.

RejectedPredictionTokens int64optional

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.

PromptTokensDetails CompletionUsagePromptTokensDetailsoptional

Breakdown of tokens used in the prompt.

AudioTokens int64optional

Audio input tokens present in the prompt.

CachedTokens int64optional

Cached tokens present in the prompt.

type Completion struct{…}

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

ID string

A unique identifier for the completion.

Choices []CompletionChoice

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

FinishReason CompletionChoiceFinishReason

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.

Accepts one of the following:

const CompletionChoiceFinishReasonStop CompletionChoiceFinishReason = "stop"

const CompletionChoiceFinishReasonLength CompletionChoiceFinishReason = "length"

const CompletionChoiceFinishReasonContentFilter CompletionChoiceFinishReason = "content_filter"

Index int64

Logprobs CompletionChoiceLogprobs

TextOffset []int64optional

TokenLogprobs []float64optional

Tokens []stringoptional

TopLogprobs []map[string, float64]optional

Text string

Created int64

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

Model string

The model used for completion.

Object TextCompletion

The object type, which is always "text_completion"

SystemFingerprint stringoptional

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.

Usage CompletionUsageoptional

Usage statistics for the completion request.

CompletionTokens int64

Number of tokens in the generated completion.

PromptTokens int64

Number of tokens in the prompt.

TotalTokens int64

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

CompletionTokensDetails CompletionUsageCompletionTokensDetailsoptional

Breakdown of tokens used in a completion.

AcceptedPredictionTokens int64optional

When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.

AudioTokens int64optional

Audio input tokens generated by the model.

ReasoningTokens int64optional

Tokens generated by the model for reasoning.

RejectedPredictionTokens int64optional

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.

PromptTokensDetails CompletionUsagePromptTokensDetailsoptional

Breakdown of tokens used in the prompt.

AudioTokens int64optional

Audio input tokens present in the prompt.

CachedTokens int64optional

Cached tokens present in the prompt.

Create completion

Go

HTTP

TypeScript

Python

Java

Go

Ruby

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  completion, err := client.Completions.New(context.TODO(), openai.CompletionNewParams{
    Model: openai.CompletionNewParamsModelGPT3_5TurboInstruct,
    Prompt: openai.CompletionNewParamsPromptUnion{
      OfString: openai.String("This is a test."),
    },
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", completion)
}

200 example

{
  "id": "id",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": {
        "text_offset": [
          0
        ],
        "token_logprobs": [
          0
        ],
        "tokens": [
          "string"
        ],
        "top_logprobs": [
          {
            "foo": 0
          }
        ]
      },
      "text": "text"
    }
  ],
  "created": 0,
  "model": "model",
  "object": "text_completion",
  "system_fingerprint": "system_fingerprint",
  "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
    }
  }
}

Returns Examples

200 example

{
  "id": "id",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": {
        "text_offset": [
          0
        ],
        "token_logprobs": [
          0
        ],
        "tokens": [
          "string"
        ],
        "top_logprobs": [
          {
            "foo": 0
          }
        ]
      },
      "text": "text"
    }
  ],
  "created": 0,
  "model": "model",
  "object": "text_completion",
  "system_fingerprint": "system_fingerprint",
  "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
    }
  }
}