开始使用

简介

MiniToolAI API 提供了一个简单的接口,可用于最先进的 AI 模型,包括自然语言处理、图像生成、文本转语音。请按照本指南学习如何生成类似人类的响应(ChatGPT),以及如何从文本描述生成图像。

创建 API 密钥

sk-*************   登录以生成 API 密钥

充值

API 请求的费用将从您的余额中扣除。

充值

授权

API 请求的头部必须包含 API 密钥。

Header: "Authorization: Bearer API_key"

 

 

 

 

ChatGPT API

为给定的聊天对话生成模型响应。

Python PHP
import requests
import json
API_Url = "https://minitoolai.com/api/chat-completions/"
API_Key = "MiniToolAI_API_Key"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_Key}"
}
data = {
    "model": "gpt-4o-mini", #gpt-4o, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
    "messages": [
		{"role": "developer", "content": "You are a helpful assistant."},
		{"role": "user", "content": "Hello"},
		{"role": "assistant", "content": "How can I help you today?"},
		{"role": "user", "content": "What's the largest U.S. state by area?"}
    ],
	"temperature": 1.0,
	"max_completion_tokens": 1000
}

response = requests.post(API_Url, headers=headers, json=data, stream=True)

#single result
print(response.text) 

#streamed
for line in response.iter_lines():
    if line:
        decode_line = line.decode('utf-8')
        print(decode_line)
<?php

$api_url = "https://minitoolai.com/api/chat-completions/";
$api_key = "MiniToolAI_API_Key"; 

$data = [
    "model" => "gpt-4o-mini", //gpt-4o, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
    "messages" => [
        ["role" => "developer", "content" => "You are a helpful assistant."],
        ["role" => "user", "content" => "Hello"],
        ["role" => "assistant", "content" => "How can I help you today?"],
        ["role" => "user", "content" => "What's the largest U.S. state by area?"],
    ],
    "temperature" => 1.0,
    "max_completion_tokens" => 1000
];

$headers = [
    "Content-Type: application/json",
    "Authorization: Bearer $api_key"
];

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $api_url);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, false); 
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));

// streamed
curl_setopt($ch, CURLOPT_WRITEFUNCTION, function($ch, $data) {
    echo $data;
    ob_flush(); 
    flush();     
    return strlen($data); 
});

$response = curl_exec($ch);

if (curl_errno($ch)) {
    echo "cURL error: " . curl_error($ch);
} 

curl_close($ch);

?>
#data with image input
data = {
    "model": "gpt-4o-mini", #gpt-4o
    "messages": [
        {"role": "developer", "content": "You are a helpful assistant."},
        {
            "role": "user", 
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg", #jpg, jpeg, png, webp or gif
                        "detail": "auto" #auto, high or low
                    }
                }
            ]
        }

    ],
    "temperature": 0.7,
    "max_completion_tokens": 300
}
//data with image input
$data = [
    "model" => "gpt-4o-mini", // gpt-4o
    "messages" => [
        ["role" => "developer", "content" => "You are a helpful assistant."],
        [
            "role" => "user",
            "content" => [
                [
                    "type" => "text",
                    "text" => "What's in this image?"
                ],
                [
                    "type" => "image_url",
                    "image_url" => [
                        "url" => "https://example.com/image.jpg", // jpg, jpeg, png, webp or gif
                        "detail" => "auto" // auto, high or low
                    ]
                ]
            ]
        ]
    ],
    "temperature" => 0.7,
    "max_completion_tokens" => 300
];

请求主体

messages 数组 必填

包含当前对话的消息列表。

  • Developer message: 开发者提供的指令,模型应遵循这些指令,而不受用户发送的消息影响。
  • User message: 终端用户发送的消息,包含提示或额外的上下文信息。
  • Assistant message: 模型根据用户消息生成的响应。

model 字符串 必填

要使用的模型 ID

可用模型: gpt-4o, gpt-4o-mini, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano

temperature 数字或 null 可选

默认值 1

用于采样的温度,范围为 0.0 到 2.0。较高的值(如 0.8)会使输出更加富有创意,而较低的值(如 0.2)会使其更加集中和确定性。

max_completion_tokens 整数或 null 可选

默认值 1000

生成完成的最大令牌数上限

响应

data: {"id":"chatcmpl-B5qoZsT8kFDNJK3UyGLiJmjv6Pp90","object":"chat.completion.chunk","created":1740734359,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_06737a9306","choices":[{"index":0,"delta":{"content":"Ok"},"logprobs":null,"finish_reason":null}],"usage":null}

data: {"id":"chatcmpl-B5qoZsT8kFDNJK3UyGLiJmjv6Pp90","object":"chat.completion.chunk","created":1740734359,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_06737a9306","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}],"usage":null}

data: {"id":"chatcmpl-B5qoZsT8kFDNJK3UyGLiJmjv6Pp90","object":"chat.completion.chunk","created":1740734359,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_06737a9306","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null}

data: {"id":"chatcmpl-B5qoZsT8kFDNJK3UyGLiJmjv6Pp90","object":"chat.completion.chunk","created":1740734359,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_06737a9306","choices":[],"usage":{"prompt_tokens":17,"completion_tokens":3,"total_tokens":20,"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}}}

data: [DONE]

 

 

 

 

文本转图像

根据提示生成图像。

Python PHP
import requests
import json
url = "https://minitoolai.com/api/texttoimage/"
API_Key = "MiniToolAI_API_Key"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_Key}"
}
data = {
    "model": "realvision",
    "prompt": "Ultra realistic portrait of a 20 year old woman, wearing an elegant black gown, joyful expression, deep shadows, cinematic composition, moody lighting",
    "negativePrompt": "unrealistic eyes, malformed features, ugly drawn",
    "scheduler": "DPM++ SDE",
    "steps": 4,
    "cfgScale": 2.0,
    "width": 1152,
    "height": 768
}
response = requests.post(url, json=data, headers=headers)
print(response.text)

'''
#response
Success:
{"status":"success","jobid":12345678,"signature":"abcxyz123"}
Error:
{"status":"error","jobid":null,"signature":null}
'''
<?php
// API URL and Key
$url = "https://minitoolai.com/api/texttoimage/";
$API_Key = "MiniToolAI_API_Key";

// Headers
$headers = [
    "Content-Type: application/json",
    "Authorization: Bearer $API_Key"
];

// Data to be sent in the request
$data = [
    "model" => "realvision",
    "prompt" => "Ultra realistic portrait of a 20 year old woman, wearing an elegant black gown, joyful expression, deep shadows, cinematic composition, moody lighting",
    "negativePrompt" => "unrealistic eyes, malformed features, ugly drawn",
    "scheduler" => "DPM++ SDE",
    "steps" => 4,
    "cfgScale" => 2.0,
    "width" => 1152,
    "height" => 768
];

// Initialize cURL session
$ch = curl_init();

// Set cURL options
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));

// Execute the cURL request
$response = curl_exec($ch);

echo $response;

// Close the cURL session
curl_close($ch);

/*
Response:
Success:
{"status":"success","jobid":12345678,"signature":"abcxyz123"}
Error:
{"status":"error","jobid":null,"signature":null}
*/
?>

获取任务状态和结果

curl -X POST https://minitoolai.com/api/texttoimage/jobs/ \
  -H "Content-Type: application/json" \
  -d '{
    "jobid": "12345678",
    "signature": "abcxyz123"
  }'

响应

{
  "status": "success",
  "image_url": "https://...",
  "message": "success"
}

model 字符串 必填

要使用的模型 ID

可用模型: "realvision", "juggernaut", "autismmix", "dreamshaper", "valhalla", "mixrealistic", "campursari", "reality", "extrarealistic", "realism", "realgirls", "realityreborn", "amigo", "simplemix", "beautifulrealistic"

prompt 字符串 必填

图像描述

negativePrompt 字符串或 null 可选

描述您希望从生成的图像中排除的内容

scheduler 字符串或 null 可选

控制图像生成过程中噪声的去除方式。

默认值 "DPM++ SDE"

可能的值包括: "Euler a", "Euler", "LMS", "Heun", "DPM2", "DPM2 a", "DPM++ 2S a", "DPM++ 2M", "DPM++ SDE", "DPM++ 2M SDE", "DPM fast", "LMS Karras", "DPM2 Karras", "DPM2 a Karras", "DPM++ 2S a Karras", "DPM++ 2M Karras", "DPM++ SDE Karras", "DPM++ 2M SDE Karras"

steps 整数或 null 可选

图像生成过程的步骤数,介于 1 到 8 之间。

默认值 4

cfgScale 数字或 null 可选

cfgScale 控制模型应在多大程度上遵循给定的文本提示。它在创造力和提示准确性之间进行平衡,范围为 1 到 7。

默认值 2

cfgScale < 4 → 更具创造性的图像, cfgScale > 4 → 更接近提示,创造性较低

width/height 整数或 null 可选

生成的图像大小,范围为 256 到 1344。

默认值 1024

 

 

 

 

API 定价

GPT 模型

每百万令牌的价格

模型 输入 输出
gpt-4o-mini $0.15 $0.60
gpt-4o $2.50 $10.00
gpt-4.1 $2.00 $8.00
gpt-4.1-mini $0.40 $1.60
gpt-4.1-nano $0.10 $0.40

图像生成

模型 每张图片的价格
所有模型 $0.0015

 

 

 

 

API 使用情况

登录以查看 API 使用情况

文本生成

图像生成