对话

POST

/v1/chat/completions

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

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

Header 参数

Content-Type

string

必需

默认值:

application/json

Authorization

string

认证信息

必需

默认值:

Bearer {{apiKey}}

Body 参数application/json

model

string

必需

messages

array [object {2}]

必需

role

string

必需

content

string

必需

temperature

number

可选

max_tokens

integer

可选

stream

boolean

可选

示例

{
    "model": "gpt-3.5-turbo",
    "messages": [
        {
            "role": "system",
            "content": "您是助手，专门为用户提供信息。"
        },
        {
            "role": "user",
            "content": "1+1=?"
        },
        {
            "role": "assistant",
            "content": "1+1=2"
        },
        {
            "role": "user",
            "content": "不对,1+1=10"
        }
    ],
    "temperature": 0.7,
    "max_tokens": 200
}

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://oneapi.popx.com/v1/chat/completions' \
--header 'Authorization;' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "gpt-3.5-turbo",
    "messages": [
        {
            "role": "system",
            "content": "您是助手，专门为用户提供信息。"
        },
        {
            "role": "user",
            "content": "1+1=?"
        },
        {
            "role": "assistant",
            "content": "1+1=2"
        },
        {
            "role": "user",
            "content": "不对,1+1=10"
        }
    ],
    "temperature": 0.7,
    "max_tokens": 200
}'

返回响应

🟢200成功

application/json

Body

string

ID 编号

必需

object

string

必需

created

integer

必需

model

string

必需

choices

array [object {4}]

必需

index

integer

必需

message

object

必需

logprobs

必需

finish_reason

string

必需

usage

object

必需

prompt_tokens

integer

必需

completion_tokens

integer

必需

total_tokens

integer

必需

prompt_tokens_details

object

必需

completion_tokens_details

object

必需

service_tier

string

必需

system_fingerprint

必需

示例

{
    "id": "chatcmpl-BNdu70C3y6OqAr5TQUUB2MDY2Xsdu",
    "object": "chat.completion",
    "created": 1744974635,
    "model": "gpt-3.5-turbo-0125",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "抱歉，您可能混淆了十进制和二进制。在十进制中，1+1=2；而在二进制中，1+1=10。如果您在二进制中计算1+1，结果确实是10。感谢您的提醒！",
                "refusal": null,
                "annotations": []
            },
            "logprobs": null,
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 50,
        "completion_tokens": 75,
        "total_tokens": 125,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "audio_tokens": 0
        },
        "completion_tokens_details": {
            "reasoning_tokens": 0,
            "audio_tokens": 0,
            "accepted_prediction_tokens": 0,
            "rejected_prediction_tokens": 0
        }
    },
    "service_tier": "default",
    "system_fingerprint": null
}

修改于 2025-04-18 12:17:21

获取模型列表