VSCode + ZooCode Tutorial: Connect Chinese AI Models (DeepSeek, Qwen, GLM) to Your Editor

[chawkian]

If you're a developer looking to integrate Chinese AI models into your VSCode workflow, ZooCode is the bridge you need. It's a VSCode extension that turns any OpenAI-compatible API endpoint into a full-featured coding assistant — chat, inline completions, and code generation — right inside your editor.

This guide walks you through connecting ZooCode to AIWave, an OpenAI-compatible API gateway that provides access to 48 Chinese AI models through a single endpoint. No multiple accounts, no separate SDK installations.

Why ZooCode?

GitHub Copilot locks you into OpenAI's models. Cursor uses Claude by default. ZooCode lets you pick any model from any vendor — and switch between them per-task. This matters because:

• No single model is best at everything
• Model quality changes monthly — the leader today may not be the leader next quarter
• Cost varies dramatically between models
• You might want Chinese models for Chinese codebases, Western models for English documentation

ZooCode decouples your editor from your model vendor. You get the best tool for each job.

Why Chinese AI Models for Coding?

• Cost efficiency. DeepSeek V4 Flash costs $0.21/$0.41 per million tokens (input/output) — roughly 10× cheaper than GPT-4o ($2.50/$10.00) while scoring 89.2% on HumanEval versus GPT-4o's 90.2%. The gap is negligible; the savings are not.
• Massive context windows. DeepSeek V4 Flash supports 1M token context. DeepSeek V4 Pro also supports 1M. You can paste entire codebases into context.
• Strong coding benchmarks. Qwen3 Coder (480B MoE) hits 88.4% on HumanEval. GLM-5.1 from Zhipu scores 87.0%.

Prerequisites

1. VSCode (latest stable)
2. ZooCode extension — install from the VSCode Extensions Marketplace (search "ZooCode")
3. AIWave account — sign up here (new accounts get $1 free credit)
4. Your API key — found in the AIWave dashboard after login

Step 1: Get Your AIWave API Key

1. Go to https://aiwave.live and log in (GitHub, Discord, Passkey, or Email)
2. Navigate to the dashboard and copy your API key
3. Note the Base URL: https://aiwave.live/v1

This Base URL is critical. ZooCode needs it to route requests through AIWave's OpenAI-compatible proxy.

Step 2: Configure ZooCode in VSCode

Open VSCode and launch ZooCode:

1. Open Command Palette: Ctrl+Shift+P (Windows/Linux) or Cmd+Shift+P (macOS)
2. Search: ZooCode: Open Settings
3. The settings panel opens in a new VSCode tab

Enter the following values:

API Provider: OpenAI Compatible
Base URL: https://aiwave.live/v1
API Key: [paste your AIWave API key]

Alternatively, if ZooCode supports JSON configuration, edit your settings file directly:

{
  "zoocode.provider": "openai-compatible",
  "zoocode.baseURL": "https://aiwave.live/v1",
  "zoocode.apiKey": "sk-your-aiwave-key-here",
  "zoocode.defaultModel": "deepseek-v4-flash",
  "zoocode.codeModel": "qwen3-coder-480b-a35b-instruct",
  "zoocode.maxTokens": 8192,
  "zoocode.temperature": 0.3,
  "zoocode.enableInlineCompletions": true,
  "zoocode.enableChat": true
}

Step 3: Model Selection Strategy

Not all models are equal for all tasks. Here's the setup that works best:

Default Model: DeepSeek V4 Flash

• Model ID: deepseek-v4-flash
• Pricing: $0.14 input / $0.28 output per 1M tokens
• Context: 1M tokens
• HumanEval: 89.2%
• Best for: General tasks. 1M context means you can throw entire project files at it.

Code Model: Qwen3 Coder 480B

• Model ID: qwen3-coder-480b-a35b-instruct
• Pricing: $0.12 input / $0.36 output per 1M tokens
• Context: 128K tokens
• HumanEval: 88.4%
• Best for: Dedicated coding tasks. Even cheaper than DeepSeek V4 Flash on input tokens.

Low-Cost Fallback: GLM-4.7 FlashX

• Model ID: glm-4.7-flashx
• Pricing: $0.06 input / $0.12 output per 1M tokens
• Context: 128K tokens
• HumanEval: 72.5%
• Best for: Quick questions, documentation lookups, non-critical tasks.

Step 4: Testing Your Setup

Create a test file:

# test_zoocode.py
def fibonacci(n):
    """Return the nth Fibonacci number."""
    if n <= 1:
        return n
    return fibonacci(n - 1) + fibonacci(n - 2)

Open the ZooCode chat and ask:

"Optimize this fibonacci function for performance."

Expected response should include memoization or iterative approach:

from functools import lru_cache

@lru_cache(maxsize=None)
def fibonacci(n):
    if n <= 1:
        return n
    return fibonacci(n - 1) + fibonacci(n - 2)

Cost Comparison: How Much Will You Actually Spend?

Let's estimate a typical workday:

Task	Tokens (avg)	Model	Cost per task
Chat question	2K in / 1K out	DeepSeek V4 Flash	~$0.0001
Code generation	5K in / 2K out	Qwen3 Coder	~$0.0002
Code review	10K in / 3K out	DeepSeek V4 Flash	~$0.0003
Documentation	8K in / 4K out	DeepSeek V4 Flash	~$0.0003

Daily total (50 interactions): ~$0.015 — roughly $0.45/month for a full-time developer. Compare that to GitHub Copilot at $10/month or Claude Pro at $20/month.

Troubleshooting

"API key not recognized": Double-check you're using your AIWave key. The Base URL must be exactly https://aiwave.live/v1.

"Model not found": The model ID must match AIWave's catalog exactly. Use deepseek-v4-flash, not deepseek-v4-flash-2025-06-01.

Slow responses: Chinese models are served from Singapore. If you're in Europe or the Americas, expect 200-500ms added latency. For latency-sensitive work, consider using the low-cost GLM-4.7 FlashXX for quick tasks.

---

Useful links:

• AIWave Model Catalog
• AIWave Pricing — current model catalog
• AIWave Discord Community

---

Resources

• AIWave developer blog
• AIWave Python SDK