Token 估算
curl --request POST \
--url https://api.minimaxi.com/v1/responses/input_tokens \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: <content-type>' \
--data '
{
"model": "MiniMax-M3",
"input": [
{
"type": "message",
"role": "user",
"content": "请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。"
}
],
"tools": [
{
"type": "function",
"name": "search_docs",
"description": "搜索 Python 标准库或第三方库的官方文档",
"parameters": {
"type": "object",
"properties": {
"library": {
"type": "string",
"description": "库名称，如 `typing`、`itertools`"
},
"query": {
"type": "string",
"description": "搜索关键词"
}
},
"required": [
"library",
"query"
]
}
},
{
"type": "function",
"name": "run_python",
"description": "在沙箱中执行 Python 代码，返回标准输出和错误信息",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "要执行的 Python 代码"
},
"timeout_seconds": {
"type": "integer",
"description": "执行超时时间（秒）",
"default": 10
}
},
"required": [
"code"
]
}
}
]
}
'import requests
url = "https://api.minimaxi.com/v1/responses/input_tokens"
payload = {
"model": "MiniMax-M3",
"input": [
{
"type": "message",
"role": "user",
"content": "请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。"
}
],
"tools": [
{
"type": "function",
"name": "search_docs",
"description": "搜索 Python 标准库或第三方库的官方文档",
"parameters": {
"type": "object",
"properties": {
"library": {
"type": "string",
"description": "库名称，如 `typing`、`itertools`"
},
"query": {
"type": "string",
"description": "搜索关键词"
}
},
"required": ["library", "query"]
}
},
{
"type": "function",
"name": "run_python",
"description": "在沙箱中执行 Python 代码，返回标准输出和错误信息",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "要执行的 Python 代码"
},
"timeout_seconds": {
"type": "integer",
"description": "执行超时时间（秒）",
"default": 10
}
},
"required": ["code"]
}
}
]
}
headers = {
"Content-Type": "<content-type>",
"Authorization": "Bearer <token>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': '<content-type>', Authorization: 'Bearer <token>'},
body: JSON.stringify({
model: 'MiniMax-M3',
input: [
{
type: 'message',
role: 'user',
content: '请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。'
}
],
tools: [
{
type: 'function',
name: 'search_docs',
description: '搜索 Python 标准库或第三方库的官方文档',
parameters: {
type: 'object',
properties: {
library: {type: 'string', description: '库名称，如 `typing`、`itertools`'},
query: {type: 'string', description: '搜索关键词'}
},
required: ['library', 'query']
}
},
{
type: 'function',
name: 'run_python',
description: '在沙箱中执行 Python 代码，返回标准输出和错误信息',
parameters: {
type: 'object',
properties: {
code: {type: 'string', description: '要执行的 Python 代码'},
timeout_seconds: {type: 'integer', description: '执行超时时间（秒）', default: 10}
},
required: ['code']
}
}
]
})
};
fetch('https://api.minimaxi.com/v1/responses/input_tokens', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.minimaxi.com/v1/responses/input_tokens",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'MiniMax-M3',
'input' => [
[
'type' => 'message',
'role' => 'user',
'content' => '请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。'
]
],
'tools' => [
[
'type' => 'function',
'name' => 'search_docs',
'description' => '搜索 Python 标准库或第三方库的官方文档',
'parameters' => [
'type' => 'object',
'properties' => [
'library' => [
'type' => 'string',
'description' => '库名称，如 `typing`、`itertools`'
],
'query' => [
'type' => 'string',
'description' => '搜索关键词'
]
],
'required' => [
'library',
'query'
]
]
],
[
'type' => 'function',
'name' => 'run_python',
'description' => '在沙箱中执行 Python 代码，返回标准输出和错误信息',
'parameters' => [
'type' => 'object',
'properties' => [
'code' => [
'type' => 'string',
'description' => '要执行的 Python 代码'
],
'timeout_seconds' => [
'type' => 'integer',
'description' => '执行超时时间（秒）',
'default' => 10
]
],
'required' => [
'code'
]
]
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.minimaxi.com/v1/responses/input_tokens"
payload := strings.NewReader("{\n \"model\": \"MiniMax-M3\",\n \"input\": [\n {\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": \"请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"name\": \"search_docs\",\n \"description\": \"搜索 Python 标准库或第三方库的官方文档\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"library\": {\n \"type\": \"string\",\n \"description\": \"库名称，如 `typing`、`itertools`\"\n },\n \"query\": {\n \"type\": \"string\",\n \"description\": \"搜索关键词\"\n }\n },\n \"required\": [\n \"library\",\n \"query\"\n ]\n }\n },\n {\n \"type\": \"function\",\n \"name\": \"run_python\",\n \"description\": \"在沙箱中执行 Python 代码，返回标准输出和错误信息\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"code\": {\n \"type\": \"string\",\n \"description\": \"要执行的 Python 代码\"\n },\n \"timeout_seconds\": {\n \"type\": \"integer\",\n \"description\": \"执行超时时间（秒）\",\n \"default\": 10\n }\n },\n \"required\": [\n \"code\"\n ]\n }\n }\n ]\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Content-Type", "<content-type>")
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.minimaxi.com/v1/responses/input_tokens")
.header("Content-Type", "<content-type>")
.header("Authorization", "Bearer <token>")
.body("{\n \"model\": \"MiniMax-M3\",\n \"input\": [\n {\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": \"请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"name\": \"search_docs\",\n \"description\": \"搜索 Python 标准库或第三方库的官方文档\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"library\": {\n \"type\": \"string\",\n \"description\": \"库名称，如 `typing`、`itertools`\"\n },\n \"query\": {\n \"type\": \"string\",\n \"description\": \"搜索关键词\"\n }\n },\n \"required\": [\n \"library\",\n \"query\"\n ]\n }\n },\n {\n \"type\": \"function\",\n \"name\": \"run_python\",\n \"description\": \"在沙箱中执行 Python 代码，返回标准输出和错误信息\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"code\": {\n \"type\": \"string\",\n \"description\": \"要执行的 Python 代码\"\n },\n \"timeout_seconds\": {\n \"type\": \"integer\",\n \"description\": \"执行超时时间（秒）\",\n \"default\": 10\n }\n },\n \"required\": [\n \"code\"\n ]\n }\n }\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.minimaxi.com/v1/responses/input_tokens")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = 'Bearer <token>'
request.body = "{\n \"model\": \"MiniMax-M3\",\n \"input\": [\n {\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": \"请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"name\": \"search_docs\",\n \"description\": \"搜索 Python 标准库或第三方库的官方文档\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"library\": {\n \"type\": \"string\",\n \"description\": \"库名称，如 `typing`、`itertools`\"\n },\n \"query\": {\n \"type\": \"string\",\n \"description\": \"搜索关键词\"\n }\n },\n \"required\": [\n \"library\",\n \"query\"\n ]\n }\n },\n {\n \"type\": \"function\",\n \"name\": \"run_python\",\n \"description\": \"在沙箱中执行 Python 代码，返回标准输出和错误信息\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"code\": {\n \"type\": \"string\",\n \"description\": \"要执行的 Python 代码\"\n },\n \"timeout_seconds\": {\n \"type\": \"integer\",\n \"description\": \"执行超时时间（秒）\",\n \"default\": 10\n }\n },\n \"required\": [\n \"code\"\n ]\n }\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"object": "response.input_tokens",
"input_tokens": 588
}OpenAI Responses API
Token 估算
估算请求的输入 token 数，不真正调用模型生成。常用于在调用主接口前评估请求成本与是否触发上下文长度上限。
POST
/
v1
/
responses
/
input_tokens
Token 估算
curl --request POST \
--url https://api.minimaxi.com/v1/responses/input_tokens \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: <content-type>' \
--data '
{
"model": "MiniMax-M3",
"input": [
{
"type": "message",
"role": "user",
"content": "请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。"
}
],
"tools": [
{
"type": "function",
"name": "search_docs",
"description": "搜索 Python 标准库或第三方库的官方文档",
"parameters": {
"type": "object",
"properties": {
"library": {
"type": "string",
"description": "库名称，如 `typing`、`itertools`"
},
"query": {
"type": "string",
"description": "搜索关键词"
}
},
"required": [
"library",
"query"
]
}
},
{
"type": "function",
"name": "run_python",
"description": "在沙箱中执行 Python 代码，返回标准输出和错误信息",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "要执行的 Python 代码"
},
"timeout_seconds": {
"type": "integer",
"description": "执行超时时间（秒）",
"default": 10
}
},
"required": [
"code"
]
}
}
]
}
'import requests
url = "https://api.minimaxi.com/v1/responses/input_tokens"
payload = {
"model": "MiniMax-M3",
"input": [
{
"type": "message",
"role": "user",
"content": "请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。"
}
],
"tools": [
{
"type": "function",
"name": "search_docs",
"description": "搜索 Python 标准库或第三方库的官方文档",
"parameters": {
"type": "object",
"properties": {
"library": {
"type": "string",
"description": "库名称，如 `typing`、`itertools`"
},
"query": {
"type": "string",
"description": "搜索关键词"
}
},
"required": ["library", "query"]
}
},
{
"type": "function",
"name": "run_python",
"description": "在沙箱中执行 Python 代码，返回标准输出和错误信息",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "要执行的 Python 代码"
},
"timeout_seconds": {
"type": "integer",
"description": "执行超时时间（秒）",
"default": 10
}
},
"required": ["code"]
}
}
]
}
headers = {
"Content-Type": "<content-type>",
"Authorization": "Bearer <token>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': '<content-type>', Authorization: 'Bearer <token>'},
body: JSON.stringify({
model: 'MiniMax-M3',
input: [
{
type: 'message',
role: 'user',
content: '请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。'
}
],
tools: [
{
type: 'function',
name: 'search_docs',
description: '搜索 Python 标准库或第三方库的官方文档',
parameters: {
type: 'object',
properties: {
library: {type: 'string', description: '库名称，如 `typing`、`itertools`'},
query: {type: 'string', description: '搜索关键词'}
},
required: ['library', 'query']
}
},
{
type: 'function',
name: 'run_python',
description: '在沙箱中执行 Python 代码，返回标准输出和错误信息',
parameters: {
type: 'object',
properties: {
code: {type: 'string', description: '要执行的 Python 代码'},
timeout_seconds: {type: 'integer', description: '执行超时时间（秒）', default: 10}
},
required: ['code']
}
}
]
})
};
fetch('https://api.minimaxi.com/v1/responses/input_tokens', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.minimaxi.com/v1/responses/input_tokens",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'MiniMax-M3',
'input' => [
[
'type' => 'message',
'role' => 'user',
'content' => '请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。'
]
],
'tools' => [
[
'type' => 'function',
'name' => 'search_docs',
'description' => '搜索 Python 标准库或第三方库的官方文档',
'parameters' => [
'type' => 'object',
'properties' => [
'library' => [
'type' => 'string',
'description' => '库名称，如 `typing`、`itertools`'
],
'query' => [
'type' => 'string',
'description' => '搜索关键词'
]
],
'required' => [
'library',
'query'
]
]
],
[
'type' => 'function',
'name' => 'run_python',
'description' => '在沙箱中执行 Python 代码，返回标准输出和错误信息',
'parameters' => [
'type' => 'object',
'properties' => [
'code' => [
'type' => 'string',
'description' => '要执行的 Python 代码'
],
'timeout_seconds' => [
'type' => 'integer',
'description' => '执行超时时间（秒）',
'default' => 10
]
],
'required' => [
'code'
]
]
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.minimaxi.com/v1/responses/input_tokens"
payload := strings.NewReader("{\n \"model\": \"MiniMax-M3\",\n \"input\": [\n {\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": \"请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"name\": \"search_docs\",\n \"description\": \"搜索 Python 标准库或第三方库的官方文档\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"library\": {\n \"type\": \"string\",\n \"description\": \"库名称，如 `typing`、`itertools`\"\n },\n \"query\": {\n \"type\": \"string\",\n \"description\": \"搜索关键词\"\n }\n },\n \"required\": [\n \"library\",\n \"query\"\n ]\n }\n },\n {\n \"type\": \"function\",\n \"name\": \"run_python\",\n \"description\": \"在沙箱中执行 Python 代码，返回标准输出和错误信息\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"code\": {\n \"type\": \"string\",\n \"description\": \"要执行的 Python 代码\"\n },\n \"timeout_seconds\": {\n \"type\": \"integer\",\n \"description\": \"执行超时时间（秒）\",\n \"default\": 10\n }\n },\n \"required\": [\n \"code\"\n ]\n }\n }\n ]\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Content-Type", "<content-type>")
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.minimaxi.com/v1/responses/input_tokens")
.header("Content-Type", "<content-type>")
.header("Authorization", "Bearer <token>")
.body("{\n \"model\": \"MiniMax-M3\",\n \"input\": [\n {\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": \"请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"name\": \"search_docs\",\n \"description\": \"搜索 Python 标准库或第三方库的官方文档\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"library\": {\n \"type\": \"string\",\n \"description\": \"库名称，如 `typing`、`itertools`\"\n },\n \"query\": {\n \"type\": \"string\",\n \"description\": \"搜索关键词\"\n }\n },\n \"required\": [\n \"library\",\n \"query\"\n ]\n }\n },\n {\n \"type\": \"function\",\n \"name\": \"run_python\",\n \"description\": \"在沙箱中执行 Python 代码，返回标准输出和错误信息\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"code\": {\n \"type\": \"string\",\n \"description\": \"要执行的 Python 代码\"\n },\n \"timeout_seconds\": {\n \"type\": \"integer\",\n \"description\": \"执行超时时间（秒）\",\n \"default\": 10\n }\n },\n \"required\": [\n \"code\"\n ]\n }\n }\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.minimaxi.com/v1/responses/input_tokens")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = 'Bearer <token>'
request.body = "{\n \"model\": \"MiniMax-M3\",\n \"input\": [\n {\n \"type\": \"message\",\n \"role\": \"user\",\n \"content\": \"请帮我用 Python 实现一个支持泛型的快速排序算法，要求：1) 原地排序节省内存；2) 处理重复元素时使用三路划分；3) 小数组切换到插入排序优化；4) 提供完整的单元测试。最后还请解释一下三路划分相比经典 Lomuto 划分在重复键场景下的优势。\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"name\": \"search_docs\",\n \"description\": \"搜索 Python 标准库或第三方库的官方文档\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"library\": {\n \"type\": \"string\",\n \"description\": \"库名称，如 `typing`、`itertools`\"\n },\n \"query\": {\n \"type\": \"string\",\n \"description\": \"搜索关键词\"\n }\n },\n \"required\": [\n \"library\",\n \"query\"\n ]\n }\n },\n {\n \"type\": \"function\",\n \"name\": \"run_python\",\n \"description\": \"在沙箱中执行 Python 代码，返回标准输出和错误信息\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"code\": {\n \"type\": \"string\",\n \"description\": \"要执行的 Python 代码\"\n },\n \"timeout_seconds\": {\n \"type\": \"integer\",\n \"description\": \"执行超时时间（秒）\",\n \"default\": 10\n }\n },\n \"required\": [\n \"code\"\n ]\n }\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"object": "response.input_tokens",
"input_tokens": 588
}授权
请求头
请求体的媒介类型，请设置为 application/json，确保请求数据的格式为 JSON
可用选项:
application/json 请求体
application/json
调用的模型名称，如 MiniMax-M3
示例:
"MiniMax-M3"
对话内容，支持简单文本或完整对话历史数组
系统指令
工具列表
Show child attributes
Show child attributes
工具选择策略：none 表示不调用任何工具；auto 表示由模型自动判断是否调用工具
可用选项:
none, auto 输出格式控制
Show child attributes
Show child attributes
推理控制。对于 MiniMax-M3，默认为 none，即关闭推理。将 effort 设置为非 none 值（minimal、low、medium 或 high），即可开启 Adaptive Thinking，但不会调节 MiniMax-M3 的推理深度。对于 M2.x 模型，推理无法关闭。
Show child attributes
Show child attributes
此页面对您有帮助吗？
⌘I