Quick Start

Three steps: buy a plan → create a subscription API key → configure your coding tool.

1. Buy a Plan

Open the subscription page and choose a Lite / Pro / Max tier and a monthly, quarterly, or yearly period.
Click subscribe and complete the payment as guided.
The subscription takes effect immediately after payment; the Coding Plan entry appears in the console, showing plan status and usage across the three windows.

Buying again while a subscription is still active queues the new subscription to start when the current period ends — no remaining time is lost.

2. Create a Subscription API Key

Go to Console → Coding Plan → API Keys.
Click create and immediately copy the full cp_live_ key (shown only once).

export SILVAMUX_CP_API_KEY="cp_live_YOUR_KEY"

Subscription-dedicated endpoints (OpenAI compatible and Anthropic compatible):

https://www.silvamux.com/api/coding-plan/v1

cp_live_ keys can only call /api/coding-plan/v1 endpoints; using them on regular endpoints returns 403 CODING_PLAN_KEY_NOT_ALLOWED. Likewise, sk_live_ keys cannot call the subscription endpoints.

3. Configure Your Coding Tool

Claude Code

export ANTHROPIC_BASE_URL="https://www.silvamux.com/api/coding-plan/v1"
export ANTHROPIC_AUTH_TOKEN="cp_live_YOUR_KEY"

Restart Claude Code and you are ready.

Cursor

In Settings → Models → OpenAI API Key, configure:

Base URL: https://www.silvamux.com/api/coding-plan/v1
API Key: cp_live_YOUR_KEY

Cline (VS Code extension)

Choose the OpenAI Compatible or Anthropic provider:

Base URL: https://www.silvamux.com/api/coding-plan/v1
API Key: cp_live_YOUR_KEY

4. Verify a Call

curl https://www.silvamux.com/api/coding-plan/v1/chat/completions \
  -H "Authorization: Bearer $SILVAMUX_CP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Write a quicksort"}]
  }'

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SILVAMUX_CP_API_KEY"],
    base_url="https://www.silvamux.com/api/coding-plan/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Write a quicksort"}],
)

print(response.choices[0].message.content)

// npm install openai
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SILVAMUX_CP_API_KEY,
  baseURL: "https://www.silvamux.com/api/coding-plan/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Write a quicksort" }],
});

console.log(response.choices[0].message.content);

// Standard library only
package main

import (
    "bytes"
    "fmt"
    "io"
    "net/http"
    "os"
)

func main() {
    payload := []byte(`{
        "model": "deepseek-v4-pro",
        "messages": [{"role": "user", "content": "Write a quicksort"}]
    }`)

    req, err := http.NewRequest("POST", "https://www.silvamux.com/api/coding-plan/v1/chat/completions", bytes.NewReader(payload))
    if err != nil {
        panic(err)
    }
    req.Header.Set("Authorization", "Bearer "+os.Getenv("SILVAMUX_CP_API_KEY"))
    req.Header.Set("Content-Type", "application/json")

    resp, err := http.DefaultClient.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()

    body, _ := io.ReadAll(resp.Body)
    fmt.Println(string(body))
}

The available model list can also be queried via GET /api/coding-plan/v1/models.