Gemini 3.5 Flash-Lite Chat API 参考

Gemini 3.5 Flash-Lite Chat Completions API 参考与在线调试：OpenAI 兼容格式，默认零思考极速响应，支持流式、Function Call、视觉。

POST /v1/chat/completions

对话补全：Gemini 3.5 Flash-Lite（OpenAI 兼容）

cURL

curl --request POST \
  --url https://api.apiyi.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-3.5-flash-lite",
  "messages": [
    {
      "role": "user",
      "content": "用一句话介绍你自己"
    }
  ]
}
'

import requests

url = "https://api.apiyi.com/v1/chat/completions"

payload = {
    "model": "gemini-3.5-flash-lite",
    "messages": [
        {
            "role": "user",
            "content": "用一句话介绍你自己"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gemini-3.5-flash-lite',
    messages: [{role: 'user', content: '用一句话介绍你自己'}]
  })
};

fetch('https://api.apiyi.com/v1/chat/completions', 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.apiyi.com/v1/chat/completions",
  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' => 'gemini-3.5-flash-lite',
    'messages' => [
        [
                'role' => 'user',
                'content' => '用一句话介绍你自己'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.apiyi.com/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"gemini-3.5-flash-lite\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"用一句话介绍你自己\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	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.apiyi.com/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gemini-3.5-flash-lite\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"用一句话介绍你自己\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.apiyi.com/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gemini-3.5-flash-lite\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"用一句话介绍你自己\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

200

{
  "id": "<string>",
  "model": "<string>",
  "choices": [
    {
      "message": {
        "role": "<string>",
        "content": "<string>",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}

右侧 Playground 可直接调试：在 Authorization 填 Bearer sk-your-api-key，点击发送即可看到响应——默认零思考，速度很快。

需要深度推理传 reasoning_effort: "high"（注意：本模型该端点不回显 reasoning_tokens，精确观测思考消耗请用 原生在线调试）。搜索 grounding、代码执行等原生工具本端点不支持。概览与实测数据见 Gemini 3.5 Flash-Lite 概览。

​

参数说明速查

参数	类型	必填	说明
model	string	✓	固定 gemini-3.5-flash-lite
messages	array	✓	OpenAI 标准消息数组；content 可为多模态数组（image_url 支持 data URL）
max_tokens	int		输出配额；开 reasoning_effort: "high" 时建议 2000+
reasoning_effort	string		high 可触发思考；usage 不回显思考量
stream	bool		SSE 流式
response_format	object		json_schema 结构化输出，实测可用
tools	array		Function Call 工具列表，实测可用

​

响应要点

• 本模型 usage.completion_tokens_details.reasoning_tokens 不回显（3.6 Flash 正常回显）——思考消耗已计入 completion_tokens
• 思考正文（reasoning_content）本端点不回显
• 模型名注意核对 gemini-3.5-flash-lite（三段小写连字符）

授权

Authorization · string · header · 必填

在请求头中添加 Authorization: Bearer YOUR_API_KEY

请求体

application/json

model · string · 必填

固定 gemini-3.5-flash-lite

messages · object[] · 必填

OpenAI 标准消息数组

Show child attributes

max_tokens · integer

输出配额；开思考时建议 2000+（思考计入输出）

temperature · number

stream · boolean

SSE 流式输出

reasoning_effort · enum<string>

思考分档

可用选项: low, medium, high

response_format · object

结构化输出，支持 json_schema

tools · object[]

Function Call 工具列表

响应

200

application/json

对话补全成功

id · string

model · string

choices · object[]

Show child attributes

usage · object

用量统计

Show child attributes