Completions

POST /openai/completions

Creates a completion for the provided prompt and parameters

cURL

curl --request POST \
  --url https://api.usesecond.com/openai/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "best_of": 1,
  "echo": false,
  "frequency_penalty": 0,
  "logit_bias": {},
  "logprobs": 123,
  "max_tokens": 16,
  "n": 1,
  "presence_penalty": 0,
  "seed": 689760,
  "stop": [
    "<string>"
  ],
  "stream": false,
  "stream_options": {
    "include_usage": false
  },
  "tempature": 1,
  "top_p": 1,
  "user": "<string>"
}
'

200

{
  "id": "<string>",
  "object": "text_completion",
  "model": "<string>",
  "choices": [
    {
      "text": "<string>",
      "index": 123,
      "logprobs": {
        "tokens": [
          "<string>"
        ],
        "token_logprobs": [
          123
        ],
        "top_logprobs": [
          {}
        ],
        "text_offset": [
          123
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  },
  "created": 1722811396105,
  "system_fingerprint": "<string>"
}

Create a completion based on the provided prompt. This endpoint requires API keys generated from the settings, standard access tokens will not work.

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model · string · required

The unique identifier of the model to be used for generating the completion

prompt · string · required

The input text that serves as the starting point for the AI to generate a completion

best_of · number · default: 1

The number of completion choices to generate and return. The model will generate multiple completions and return the best one(s) based on the specified criteria

echo · boolean · default: false

When set to true, the API will include the original prompt in the completion response, effectively echoing it back

frequency_penalty · number · default: 0

A value between -2.0 and 2.0 that penalizes new tokens based on their frequency in the text so far. Higher values decrease the model's likelihood to repeat the same lines verbatim

logit_bias · object

A dictionary that allows fine-tuning the likelihood of specified tokens appearing in the completion. Each key is a token, and the value is the bias (between -100 and 100)

Show child attributes

logprobs · number

The number of most likely tokens to return with their log probabilities. If specified, the API will return a list of the most likely tokens for each position

max_tokens · number · default: 16

The maximum number of tokens to generate in the completion. The total length of input tokens and generated tokens is limited by the model's context length

n · number · default: 1

The number of completions to generate for each prompt. Note that this may conflict with best_of if both are specified

presence_penalty · number · default: 0

A value between -2.0 and 2.0 that penalizes new tokens based on whether they appear in the text so far. Positive values increase the model's likelihood to talk about new topics

seed · number · default: 689760

A seed for deterministic sampling. Using the same seed with the same parameters will generate the same completion

stop · string[]

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence

Maximum array length: 4

stream · boolean · default: false

If set to true, partial message deltas will be sent as data-only server-sent events. Tokens will be sent as they become available

stream_options · object

Additional options to configure the behavior of streaming responses

Show child attributes

tempature · number · default: 1

A value between 0 and 2 that controls the randomness of the completion. Lower values make the output more focused and deterministic, while higher values make it more random

top_p · number · default: 1

An alternative to temperature, called nucleus sampling. It considers the results of the tokens with top_p probability mass. 0.1 means only the tokens comprising the top 10% probability mass are considered

user · string

A unique identifier representing your end-user, which can help the API to monitor and detect abuse

Response

200

application/json

Successful response

id · string · required

object · enum<string> · required

Available options: text_completion

model · string · required

choices · object[] · required

Show child attributes

usage · object · required

Show child attributes

created · number · default: 1722811396105

system_fingerprint · string