Legacy OpenAI-Compatible Text Completions Endpoint

POST /v1/completions provides the legacy OpenAI text completions format. For most use cases, prefer POST /v1/chat/completions instead.

The /v1/completions endpoint supports the older OpenAI text completion format, which predates the chat completions API. You can use it for backward compatibility with existing tools and integrations that were built against the original completions interface before the chat format became the standard.

For most use cases, prefer the /v1/chat/completions endpoint. This endpoint is provided for backward compatibility with older integrations.

Request

POST https://kiosapi.com/v1/completions

Headers

Header	Required	Description
Content-Type	Yes	application/json
Authorization	Yes	Bearer sk-xxx

Request Body

model · string · required

Model name (e.g. gpt-3.5-turbo-instruct).

prompt · string · required

Input text prompt to complete.

temperature · number

Sampling temperature between 0 and 2. Higher values produce more random output.

top_p · number

Nucleus sampling probability mass. Use as an alternative to temperature.

stream · boolean

Set to true to receive a streamed response using server-sent events.

max_tokens · number

Maximum number of tokens to generate in the completion.

n · number

How many completions to generate for each prompt.

presence_penalty · number

Number between -2.0 and 2.0. Positive values penalise new tokens based on whether they appear in the text so far.

frequency_penalty · number

Number between -2.0 and 2.0. Positive values penalise new tokens based on their existing frequency in the text.

logprobs · number

Return log probabilities of the most likely tokens. Pass an integer to specify how many tokens to return.

user · string

A unique identifier for the end-user, which can help with monitoring and abuse detection.

Example Request

curl https://kiosapi.com/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "The weather is very nice today",
    "temperature": 0.7,
    "max_tokens": 100,
    "top_p": 1,
    "frequency_penalty": 0,
    "presence_penalty": 0
  }'

Response

{
  "id": "cmpl-A1tJLfyQgj1j2GpvhA6QcMCZKwRtw",
  "object": "text_completion",
  "created": 1725014307,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [
    {
      "text": ", perfect for going out\n\nYes, the weather is very good today, perfect for a trip.",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 6,
    "completion_tokens": 25,
    "total_tokens": 31
  }
}