Chat Completions API

POST

https://api.gptnb.me/v1/completions

Given a prompt, the model will return one or more predicted completions along with the probabilities of alternative tokens at each position. Most developer should use our Chat Completions API to leverage our best and newest models.

Request

Header Params

Body Params application/json

Example

{
  "model": "gpt-3.5-turbo-instruct",
  "prompt": "Say this is a test",
  "max_tokens": 7,
  "temperature": 0,
  "top_p": 1,
  "n": 1,
  "stream": false,
  "logprobs": null,
  "stop": "\n"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://api.gptnb.me/v1/completions' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
  "model": "gpt-3.5-turbo-instruct",
  "prompt": "Say this is a test",
  "max_tokens": 7,
  "temperature": 0,
  "top_p": 1,
  "n": 1,
  "stream": false,
  "logprobs": null,
  "stop": "\n"
}'

Responses

🟢200Ok

application/json

Bodyapplication/json

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
    }
}

Modified at 2024-02-29 13:04:12

gpt-4-vision-preview

Submit swap_face task