Text Completions (Legacy)

POST /v1/completions

The classic text-in → text-out completion endpoint (no conversation structure). For new projects, prefer Chat Completions.

RequestREQUEST

POSThttps://test.kailin.com.cn/v1/completions

API KeyStored only in your browser, never uploaded

Body (JSON)Non-streaming{ "model": "gpt-3.5-turbo-instruct", "prompt": "Three keywords about artificial intelligence:", "max_tokens": 30 }

ResponseRESPONSE

Fill in the request and hit Send — the response shows up here

Request

curl https://test.kailin.com.cn/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-token" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Three keywords about artificial intelligence:",
    "max_tokens": 30,
    "temperature": 0.8
  }'

Request Body

Parameter	Type	Required	Description
model	string	Yes	Must be a completion-style model
prompt	string / array	Yes	Text to continue; pass an array for batch requests
stream	boolean	No	Stream output (SSE), default false
max_tokens	number	No	Max tokens to generate
temperature	number	No	Sampling temperature 0–2
top_p	number	No	Nucleus sampling
n	integer	No	Number of completions to generate
stop	string / array	No	Stop sequences
echo	boolean	No	Echo the prompt back in the result
logprobs	integer	No	Return per-token log probabilities (max 5)
frequency_penalty / presence_penalty	number	No	Repetition penalties
seed	integer	No	Random seed

Response

{
  "id": "cmpl-xxx",
  "object": "text_completion",
  "created": 1730000000,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [
    {
      "index": 0,
      "text": " deep learning, neural networks, and natural language processing.",
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 18,
    "total_tokens": 30
  }
}

caution

Not every channel offers completion-style models. If the model name errors out, check the available list with GET /v1/models first.