Create chat completion (streaming)

Developing

POST

/v1/chat/completions

Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position.
Create completions for the provided prompt and parameters
Official documentation: https://platform.openai.com/docs/api-reference/chat/create

Request

Header Params

Body Params application/json

Example

{
    "model": "gpt-5-mini",
    "max_tokens": 1000,
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "hello"
        }
    ],
    "temperature": 1.0,
    "stream": true,
    "stream_options": {
        "include_usage": true
    }
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: {{Authorization}}' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gpt-5-mini",
    "max_tokens": 1000,
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "hello"
        }
    ],
    "temperature": 1.0,
    "stream": true,
    "stream_options": {
        "include_usage": true
    }
}'

Responses

🟢200成功

application/json

Bodyapplication/json

Example

{}

Modified at 2026-10-19 10:10:04

Edit image

Create chat completion (qwen-mt-turbo)