Creation completed

POST

/v1/completions

Given a prompt, the model will return one or more predicted completions, and can also return the probability of alternative tokens at each position.

Create a completion for the provided prompt and parameters

https://platform.openai.com/docs/api-reference/completions

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Header Params

Body Params application/json

Examples

Responses

🟢200Ok

application/json

Body

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST '/v1/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{\n    \"model\": \"gpt-3.5-turbo-instruct\",\n    \"prompt\": \"Hello,\",\n    \"max_tokens\": 30,\n    \"temperature\": 0\n  }'

Response Example

{
    "id": "cmpl-ByvHP6AWeB1L5vWZSPNHsB12sU9db",
    "object": "text_completion",
    "created": 1753859563,
    "model": "gpt-3.5-turbo-instruct",
    "choices": [
        {
            "index": 0,
            "logprobs": null,
            "finish_reason": "length",
            "text": "I am Xiaoice, nice to meet you. I am an artificial intelligence assistant that can respond"
        }
    ],
    "usage": {
        "prompt_tokens": 3,
        "completion_tokens": 30,
        "total_tokens": 33
    }
}

Modified at 2026-03-06 15:34:51

Completion object

Embedded Object