Context Cache Creation

1. Overview

Creates a context cache. After obtaining the cache id from this endpoint, pass it as context_id to the Context Cache Chat Completion endpoint.

2. Request

• Method:POST

• Endpoint:

  https://gateway.serevixai.ai/v1/context/create
  

---

3. Parameters

3.1 Header Parameters

Parameter	Type	Required	Description	Example
Content-Type	string	Yes	Sets the request content type. It must be application/json	application/json
Accept	string	Yes	Sets the response content type. The recommended value is application/json	application/json
Authorization	string	Yes	API key required for authentication, in the format Bearer $YOUR_API_KEY.	Bearer $YOUR_API_KEY

---

3.2 Body Parameters (application/json)

Parameter	Type	Required	Description	Example
model	string	Yes	The model ID to use. See Model List for available versions, such as Doubao-1.5-pro-32k.	Doubao-1.5-pro-32k
messages	array	Yes	Messages used to initialize or store information in the cache, in an OpenAI-compatible format. Each item contains role and content.	[{"role": "system","content": "you are a helpful asssistant"}]
role	string	No	Message role. Supported values: system, user, and assistant.	system
content	string	No	The message content.	you are a helpful asssistant
mode	string	No	Context cache type. See the official documentation for Context Caching (Context API) Overview. Supported values are session cache session and prefix cache common_prefix.	session
ttl	number	No	TTL in seconds. The timer starts when the cache is created and resets each time the cache is used. When the TTL expires, the cached information is removed. The allowed range is 1 hour to 7 days, i.e. [3600, 604800].	86400

---

4. Request Examples

HTTPShellGo

POST /v1/context/create
Content-Type: application/json
Accept: application/json
Authorization: Bearer $YOUR_API_KEY

{
    "model": "Doubao-1.5-pro-32k",
    "messages": [
        {
            "role": "system",
            "content": "Please act as a friendly customer support agent"
        },
        {
            "role": "user",
            "content": "Hello"
        }
    ],
    "mode":"session",
    "ttl": 3600
}

curl https://gateway.serevixai.ai/v1/context/create \
    -H "Content-Type: application/json" \
    -H "Accept: application/json" \
    -H "Authorization: Bearer $YOUR_API_KEY" \
    -d "{
    \"model\": \"Doubao-1.5-pro-32k\",
    \"messages\": [{
            \"role\": \"system\",
            \"content\": \"Please act as a friendly customer support agent\"
        },
        {
            \"role\": \"user\",
            \"content\": \"Hello\"
        }
    ],
    \"mode\": \"session\",
    \"ttl\": 3600
}"

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "strings"
)

const (
    YOUR_API_KEY    = "sk-123456789012345678901234567890123456789012345678"
    REQUEST_PAYLOAD = `{
    "model": "Doubao-1.5-pro-32k",
    "messages": [{
            "role": "system",
            "content": "Please act as a friendly customer support agent"
        },
        {
            "role": "user",
            "content": "Hello"
        }
    ],
    "mode": "session",
    "ttl": 3600
}`
)

func main() {

    requestURL := "https://gateway.serevixai.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. Response Example

{
    "id": "ctx-20241211104333-12345",
    "ttl": 3600,
    "truncation_strategy": {
        "type": "rolling_tokens",
        "rolling_tokens": true
    },
    "usage": {
        "prompt_tokens": 8,
        "completion_tokens": 0,
        "total_tokens": 8,
        "prompt_tokens_details": {
            "cached_tokens": 0
        }
    },
    "mode": "session"
}