OpenCode + Chinese AI Models: Setup Guide (DeepSeek, GLM, Kimi)

[chawkian]

OpenCode + Chinese AI Models: Setup Guide for DeepSeek, GLM & Kimi

OpenCode is a terminal-native AI coding assistant — no IDE required. You interact with it entirely through your shell, making it ideal for SSH sessions, headless servers, and developers who live in the terminal.

Chinese AI models from DeepSeek, Zhipu (GLM), and Moonshot (Kimi) are serious contenders for coding tasks at a fraction of the cost of GPT-4o or Claude. This guide covers the full setup.

Why OpenCode for Chinese Models?

OpenCode works with any OpenAI-compatible API. Since AIWave exposes Chinese models through a standard endpoint, the integration is straightforward — set a base URL and API key, then pick your model.

Practical advantages of the terminal-first approach:

• SSH workflows: AI coding on remote servers without forwarding ports or VS Code Remote
• Speed: No Electron overhead, responses render directly in terminal
• Scripting: Pipe file contents, redirect output, chain with other CLI tools

Installation

go install github.com/opencode-ai/opencode@latest

Or without Go:

curl -fsSL https://opencode.ai/install | bash

Verify: opencode --version

Configuration

Create ~/.config/opencode/config.json:

{
  "provider": "openai",
  "base_url": "https://aiwave.live/v1",
  "api_key": "***",
  "model": "deepseek-chat"
}

Switch models with flags:

opencode --model deepseek-chat   # Fast, cheap
opencode --model glm-5            # Stronger reasoning
opencode --model kimi-k2.6           # Good balance

Or define multiple in config:

{
  "provider": "openai",
  "base_url": "https://aiwave.live/v1",
  "api_key": "***",
  "models": {
    "fast": "deepseek-chat",
    "reasoning": "glm-5",
    "balanced": "kimi-k2.6"
  },
  "default_model": "fast"
}

Then use opencode --model reasoning or opencode --model balanced.

Model Comparison

	DeepSeek V4 Flash	GLM-5	Kimi K2.6
Input (USD/1M tokens)	$0.21	$1.55	$1.09
Output (USD/1M tokens)	$0.41	$4.96	$4.60
Context window	1M	128K	128K
Coding strength	Excellent	Very good	Good
Terminal latency	Sub-second	1-2s	1-3s

Prices from AIWave pricing.

Cost Estimates

Terminal sessions use shorter contexts than IDE workflows. Assumptions: 15 prompts per session, 1K input + 500 output tokens per prompt.

Model	Per Query	Per Session (15 prompts)	Monthly (20 sessions)
DeepSeek V4 Flash	$0.00041	$0.0062	$0.12
GLM-5	$0.00403	$0.0605	$1.21
Kimi K2.6	$0.00339	$0.0508	$1.02
GPT-4o (reference)	$0.00750	$0.1125	$2.25

Formula: (1000/1M x input_price) + (500/1M x output_price) per query, x15 prompts, x20 sessions.

At the live AIWave rates above, a month of 20 terminal sessions with DeepSeek V4 Flash is about $0.12. A $1 credit covers roughly 160 sessions at the stated assumptions — about eight months at 20 sessions per month.

Practical Usage

# Code generation
opencode "Add input validation to parse_config in config.py"

# Analyze logs
cat error.log | opencode "What caused this error and how to fix it?"

# Code review
git diff main | opencode "Review this diff for bugs"

Troubleshooting

Connection refused: Verify base URL ends with /v1 (no trailing slash). Test with curl first:

curl https://aiwave.live/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-chat","messages":[{"role":"user","content":"hello"}]}'

**Mode

Read full article on AIWave blog.

---

AIWave - 48 AI models, one API key. $1 free credit.

---

Resources

• AIWave developer blog
• AIWave Python SDK