Norvo AI User Guide

Configuration Overview

Getting Started

Follow these steps to redeem your code and create an API key.

1Access Redeem Page

Log in to the platform and navigate to the redeem page from the navigation menu.

2Enter Redeem Code

Input your redeem code in the designated field and click the redeem button to activate your account balance.

3Create API Key

After redeeming, go to the API Keys section and Click create API key.

Give it a name and select a group you want to use, then click Create. Your API key will be displayed. Copy and save it securely - you'll need it for API calls.

5How to Use

Use your API key in your code. Set the base URL to https://aix.norvo.top and include your API key in the authorization header.

Quick Start

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://aix.norvo.top",
    api_key="YOUR_API_KEY"
)

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

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

cURL

curl https://aix.norvo.top/chat/completions \ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \ \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://aix.norvo.top",
  apiKey: "YOUR_API_KEY",
});

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

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

Tool Integration

Claude Code

Claude Code is an AI coding assistant that runs in the terminal.

Install Claude Code CLI from https://github.com/anthropics/claude-code.

Linux / Mac:

export ANTHROPIC_BASE_URL=https://aix.norvo.top
export ANTHROPIC_AUTH_TOKEN=<your API Key>
export ANTHROPIC_MODEL=deepseek-v4-pro
export ANTHROPIC_DEFAULT_OPUS_MODEL=deepseek-v4-pro
export ANTHROPIC_DEFAULT_SONNET_MODEL=deepseek-v4-pro
export ANTHROPIC_DEFAULT_HAIKU_MODEL=deepseek-v4-pro
export CLAUDE_CODE_SUBAGENT_MODEL=deepseek-v4-pro
export CLAUDE_CODE_EFFORT_LEVEL=max

Windows PowerShell:

$env:ANTHROPIC_BASE_URL="https://aix.norvo.top"
$env:ANTHROPIC_AUTH_TOKEN="<your API Key>"
$env:ANTHROPIC_MODEL="deepseek-v4-pro"
$env:ANTHROPIC_DEFAULT_OPUS_MODEL="deepseek-v4-pro"
$env:ANTHROPIC_DEFAULT_SONNET_MODEL="deepseek-v4-pro"
$env:ANTHROPIC_DEFAULT_HAIKU_MODEL="deepseek-v4-pro"
$env:CLAUDE_CODE_SUBAGENT_MODEL="deepseek-v4-pro"
$env:CLAUDE_CODE_EFFORT_LEVEL="max"

Then enter your project directory and run Claude Code:

cd /path/to/my-project
claude

Claude Code via CC-Switch

Install CC-Switch from https://github.com/farion1231/cc-switch.

1. Select Claude tab panel
2. Click the + icon to add a new provider
3. Set Provider Preset to Custom Configuration
4. Enter a provider name, for example Norvo Deepseek
5. Set API Endpoint to https://aix.norvo.top, then paste your API key
6. Set all model inputs to deepseek-v4-pro or another supported model name
7. Click `+ Add`

Then enter your project directory and run Claude Code:

cd /path/to/my-project
claude

Codex via CC-Switch

Install Codex CLI from https://github.com/openai/codex.

Install CC-Switch from https://github.com/farion1231/cc-switch.

1. Select Codex tab panel
2. Click the + icon to add a new provider
3. Set Provider Preset to Custom Configuration
4. Enter a provider name, for example Norvo gpt
5. Set API Endpoint to https://aix.norvo.top, then paste your API key
6. Set model to gpt-5.4 or gpt-5.5 or another supported model name
7. Click `+ Add`

Then enter your project directory and run Codex:

cd /path/to/my-project
codex

Cherry Studio

Install it from https://github.com/CherryHQ/cherry-studio.

1. Go to Settings → Model Provider
2. Click "+ Add"
3. Enter a name, choose Anthropic or OpenAI as the protocol type, then click OK
4. Select the provider you just created. Set API Host to https://aix.norvo.top, then paste your API key
5. Click Fetch model list and add the models shown in the list
6. Go to Home, create an assistant or topic, select a model via @ under the input box, and start using it

Common Errors