API Compatibility

OpenAI · Completions (Legacy)

Generates a text completion based on the provided prompt.#

POST/v1/completions

When streaming is enabled, the response will be sent as a server-sent event (SSE) stream of CompletionChunkResponse objects; otherwise, a single JSON CompletionResponse is returned.

The endpoint produces two types of responses:

• application/json: A non-streaming response containing a single CompletionResponse object.

• text/event-stream: A streaming response in which each event contains a CompletionChunkResponse object.

This endpoint implements the OpenAI completions API specification. For complete reference, please see the official OpenAI documentation: https://platform.openai.com/docs/api-reference/completions/create

Request body

application/json ·

Property	Type	Description
`model`	string	The ID of the model used for the text completion. If not specified, the default model will be used.
`prompt`required	object	The prompt(s) to generate completions for. Can be a string or an array of strings.
`suffix`	string	A suffix that comes after a completion of inserted text. This parameter is only supported for gpt-3.5-turbo-instruct.
`max_tokens`	object (int32)	The maximum number of tokens that can be generated in the completion. Defaults to 16.
`temperature`	object (double)	What sampling temperature to use, between 0 and 2. Defaults to 1.
`top_p`	object (double)	An alternative to sampling with temperature using nucleus sampling, where the model considers the tokens with top_p probability mass. Defaults to 1.
`n`	object (int32)	How many completions to generate for each prompt. Defaults to 1.
`stream`	boolean	Whether to stream back partial progress. Defaults to false.
`stream_options`		Options for streaming response. Only set when Stream is true.
`logprobs`	object (int32)	Include the log probabilities on the logprobs most likely tokens, as well as the chosen tokens. Defaults to null.
`echo`	boolean	Echo back the prompt in addition to the completion. Defaults to false.
`stop`	object	Up to 4 sequences where the API will stop generating further tokens. Can be a string or an array of strings. Defaults to null.
`presence_penalty`	object (double)	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far. Defaults to 0.
`frequency_penalty`	object (double)	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far. Defaults to 0.
`best_of`	object (int32)	Generates best_of completions server-side and returns the 'best' (the one with the highest log probability per token). Defaults to 1.
`logit_bias`	object	Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object mapping token IDs (as strings) to bias values between -100 and 100. Defaults to null.
`user`	string	A unique identifier representing your end-user. Defaults to null.
`seed`	object (int32)	If specified, attempts to sample deterministically. Defaults to null.

Responses

Status	Type	Description
200		OK
400		Bad Request
500	application/json	Internal Server Error
404		Not Found

curl -X POST "$LMKIT_ONE_URL/v1/completions" \
  -H "Authorization: Bearer $LMKIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "string",
  "prompt": {},
  "suffix": "string",
  "max_tokens": "string",
  "temperature": "string"
}'