Open AI (ChatGPT)
🇺🇸 English
  • 🇺🇸 English
  • 🇯🇵 Japanese
  • 🇵🇹 Portuguese
  • 🇰🇷 Korea
  • 🇩🇪 German
  1. Completions
Open AI (ChatGPT)
🇺🇸 English
  • 🇺🇸 English
  • 🇯🇵 Japanese
  • 🇵🇹 Portuguese
  • 🇰🇷 Korea
  • 🇩🇪 German
  • README
  • Introduction
  • Authentication
  • Making requests
  • Streaming
  • Debugging requests
  • Backward compatibility
  • Administration
  • Audio
    • Create speech
      POST
    • Create transcription
      POST
    • Create translation
      POST
  • Chat
    • Create chat completion
      POST
  • Embeddings
    • Create embeddings
      POST
  • Fine-tuning
    • Create fine-tuning job
      POST
    • List fine-tuning jobs
      GET
    • List fine-tuning events
      GET
    • List fine-tuning checkpoints
      GET
    • Retrieve fine-tuning job
      GET
    • Cancel fine-tuning
      POST
  • Batch
    • Create batch
      POST
    • Retrieve batch
      GET
    • Cancel batch
      POST
    • List batch
      GET
  • Files
    • README
    • Upload file
    • List files
    • Retrieve file
    • Delete file
    • Retrieve file content
  • Uploads
    • Create upload
    • Add upload part
    • Complete upload
  • Images
    • README
    • Create image
    • Create image edit
    • Create image variation
  • Models
    • List models
    • Retrieve model
    • Delete a fine-tuned model
  • Moderations
    • Create moderation
  • Invites
    • List invites
    • Create invite
    • Retrieve invite
    • Delete invite
  • Users
    • List users
    • Modify user
    • Retrieve user
  • Projects
    • List projects
    • Create project
    • Retrieve project
    • Modify project
    • Archive project
  • Project users
    • List project users
    • Create project user
    • Retrieve project user
    • Modify project user
    • Delete project user
    • Create project service account
  • Project service accounts
    • List project service accounts
    • Create project service account
    • Retrieve project service account
    • Delete project service account
  • Project API keys
    • List project API keys
    • Retrieve project API key
    • Delete project API key
  • Project rate limits
    • List project rate limits
    • Modify project rate limit
  • Audit logs
    • List audit logs
  • Usage
    • Completions
    • Embeddings
    • Moderations
    • Images
    • Audio speeches
    • Audio transcriptions
    • Vector stores
    • Code interpreter sessions
    • Costs
  • Completions
    • Create completion
      POST
  • Assistants (v1)
    • Create assistant (v1)
    • Create assistant file (v1)
    • List assistants (v1)
    • List assistant files (v1)
    • Retrieve assistant (v1)
    • Retrieve assistant file (v1)
    • Modify assistant (v1)
    • Delete assistant (v1)
    • Delete assistant file (v1)
  • Threads (v1)
    • Create thread (v1)
    • Retrieve thread (v1)
    • Modify thread (v1)
    • Delete thread (v1)
  • Messages (v1)
    • Create message (v1)
    • List messages (v1)
    • List message files (v1)
    • Retrieve message (v1)
    • Retrieve message file (v1)
    • Modify message (v1)
  • Runs (v1)
    • Create run (v1)
    • Create thread and run (v1)
    • List runs (v1)
    • List run steps (v1)
    • Retrieve run (v1)
    • Retrieve run step (v1)
    • Modify run (v1)
    • Submit tool outputs to run (v1)
    • Cancel a run (v1)
  1. Completions

Create completion

POST
https://api.openai.com/v1/completions
Creates a completion for the provided prompt and parameters.
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST 'https://api.openai.com/v1/completions' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "text-davinci-003",
  "prompt": "Say this is a test",
  "max_tokens": 7,
  "temperature": 0,
  "top_p": 1,
  "n": 1,
  "stream": false,
  "logprobs": null,
  "stop": "\n"
}'
Response Response Example
{
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
  "object": "text_completion",
  "created": 1589478378,
  "model": "text-davinci-003",
  "choices": [
    {
      "text": "\n\nThis is indeed a test",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}

Request

Authorization
Provide your bearer token in the
Authorization
header when making requests to protected resources.
Example:
Authorization: Bearer ********************
Header Params
Authorization
string 
optional
Example:
Bearer {{YOUR_API_KEY}}
Body Params application/json
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 
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.

suffix
string 
optional
The suffix that comes after a completion of inserted text.
max_tokens
integer 
optional
The maximum number of tokens to generate 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.
temperature
integer 
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.
top_p
integer 
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.
n
integer 
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.
stream
boolean 
optional
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.
logprobs
null 
optional
Include the log probabilities on the logprobs most likely 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.
echo
string 
optional
Echo back the prompt in addition to the completion
presence_penalty
number 
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.
frequency_penalty
number 
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.
best_of
integer 
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.
logit_bias
string 
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 (which works for both GPT-2 and GPT-3) 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.

stop
string 
optional
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
user
string 
optional
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
Examples

Responses

🟢200Ok
application/json
Body
id
string 
required
object
string 
required
created
integer 
required
model
string 
required
choices
array [object {4}] 
required
text
string 
optional
index
integer 
optional
logprobs
null 
optional
finish_reason
string 
optional
usage
object 
required
prompt_tokens
integer 
required
completion_tokens
integer 
required
total_tokens
integer 
required
Modified at 2024-12-12 07:52:38
Previous
Costs
Next
Create assistant (v1)
Built with