gpt-4o

POST

https://api.b3n.fun/v1/chat/completions

请求参数

Header 参数

Authorization

string

可选

示例值:

Body 参数application/json

model

string

必需

response_format

object

必需

type

string

必需

messages

array [object {2}]

必需

role

string

必需

content

string

必需

示例

{
  "model": "gpt-4o",
  "response_format": {
    "type": "json_object"
  },
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant designed to output JSON."
    },
    {
      "role": "user",
      "content": "Who won the world series in 2020?"
    }
  ]
}

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.b3n.fun/v1/chat/completions' \
--header 'Authorization: sk-abc' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "gpt-4o",
  "response_format": {
    "type": "json_object"
  },
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant designed to output JSON."
    },
    {
      "role": "user",
      "content": "Who won the world series in 2020?"
    }
  ]
}'

返回响应

🟢200成功

application/json

Body

string

必需

object

string

必需

created

integer

必需

model

string

必需

choices

array [object {4}]

必需

index

integer

可选

message

object

可选

logprobs

null

可选

finish_reason

string

可选

usage

object

必需

prompt_tokens

integer

必需

completion_tokens

integer

必需

total_tokens

integer

必需

示例

{
  "id": "chatcmpl-9RL23uLmhKznke8ADyo6U62sbYEPV",
  "object": "chat.completion",
  "created": 1716302731,
  "model": "gpt-4o-2024-05-13",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "{\n  \"year\": 2020,\n  \"winner\": \"Los Angeles Dodgers\"\n}"
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 31,
    "completion_tokens": 19,
    "total_tokens": 50
  },
  "system_fingerprint": "fp_927397958d"
}

修改于 2024-05-21 14:45:30

gpt-4-turbo

gpt-3.5-turbo