上下文缓存创建
1. 概述
显示创建上下文缓存,通过本接口获得缓存id字段后,在对话生成接口中通过携带context_id使用。
模型列表:
gemini-2.0-flashgemini-2.5-flashgemini-2.5-progemini-2.5-flash-litegemini-2.5-flash-lite-preview-06-17gemini-2.5-flash-thinking(输出思考过程)gemini-2.5-pro-thinking(输出思考过程)gemini-3-pro-preview
本 API 支持的缓存token数有限制,通常不得小于1024或4096token数。
2. 请求说明
请求方法:
POST请求地址:
https://gateway.theturbo.ai/v1/context/create
3. 请求参数
3.1 Header 参数
Content-Type
string
是
设置请求头类型,必须为 application/json
application/json
Accept
string
是
设置响应类型,建议统一为 application/json
application/json
Authorization
string
是
身份验证所需的 API_KEY,格式 Bearer $YOUR_API_KEY
Bearer $YOUR_API_KEY
3.2 Body 参数 (application/json)
messages
array
是
用于初始化或希望服务在缓存中存储的信息,格式与 OpenAI 兼容。数组中的每个对象包含 role(角色) 与 content(内容)。
[{"role": "system","content": "you are a helpful asssistant"}]
role
string
否
消息角色,可选值:system、user、assistant。
system
content
string
否
消息的具体内容。
you are a helpful asssistant
ttl
number
否
过期时长,单位为秒。
300
4. 请求示例
POST /v1/context/create
Content-Type: application/json
Accept: application/json
Authorization: Bearer $YOUR_API_KEY
{
"model": "gemini-2.0-flash",
"messages": [
{
"role": "system",
"content": "请扮演一位友好的客服。... 不少于4096tokens ..."
},
{
"role": "user",
"content": "你好"
}
],
"ttl": 300
}curl https://gateway.theturbo.ai/v1/context/create \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "Authorization: Bearer $YOUR_API_KEY" \
-d "{
\"model\": \"gemini-2.0-flash\",
\"messages\": [{
\"role\": \"system\",
\"content\": \"请扮演一位友好的客服。... 不少于4096tokens ...\"
},
{
\"role\": \"user\",
\"content\": \"你好\"
}
],
\"ttl\": 300
}"package main
import (
"fmt"
"io/ioutil"
"net/http"
"strings"
)
const (
YOUR_API_KEY = "sk-123456789012345678901234567890123456789012345678"
REQUEST_PAYLOAD = `{
"model": "gemini-2.0-flash",
"messages": [{
"role": "system",
"content": "请扮演一位友好的客服。... 不少于4096tokens ..."
},
{
"role": "user",
"content": "你好"
}
],
"mode": "session",
"ttl": 3600
}`
)
func main() {
requestURL := "https://gateway.theturbo.ai/v1/context/create"
requestMethod := "POST"
requestPayload := strings.NewReader(REQUEST_PAYLOAD)
req, err := http.NewRequest(requestMethod, requestURL, requestPayload)
if err != nil {
fmt.Println("Create request failed, err: ", err)
return
}
req.Header.Add("Content-Type", "application/json")
req.Header.Add("Accept", "application/json")
req.Header.Add("Authorization", "Bearer "+YOUR_API_KEY)
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
fmt.Println("Do request failed, err: ", err)
return
}
defer resp.Body.Close()
respBodyBytes, err := ioutil.ReadAll(resp.Body)
if err != nil {
fmt.Println("Read response body failed, err: ", err)
return
}
fmt.Println(string(respBodyBytes))
}5. 响应示例
{
"id": "projects/37021971161/locations/global/cachedContents/1692176707571679232",
"ttl": 300,
"usage": {
"prompt_tokens": 4375,
"completion_tokens": 0,
"total_tokens": 0,
"cache_creation_input_tokens": 4375
}
}最后更新于