OpenCode CLI Tutorial: Use DeepSeek API in Your Terminal (Setup, Model Selection & Cost Guide)

[chawkian]

Using DeepSeek API with OpenCode CLI in Your Terminal

If you live in the terminal, you want your AI coding assistant to live there too. OpenCode CLI is a terminal-based coding assistant that works with any OpenAI-compatible API. Pair it with DeepSeek models through AIWave, and you get a fast, cheap, and powerful coding workflow ??no browser, no IDE plugin, just your shell.

This guide covers installation, configuration, model selection, and practical usage patterns.

---

What Is OpenCode CLI?

OpenCode is an open-source terminal AI assistant. It provides:

• Inline code explanations ??pipe code through it
• Shell command suggestions ??describe what you want, get the command
• File-aware chat ??it reads your project files
• Model switching ??swap models mid-conversation

It's designed for developers who prefer vim/neovim or just don't want another Electron app eating RAM.

---

Installation

# macOS / Linux (Homebrew)
brew install opencode

# Or download directly
curl -fsSL https://opencode.dev/install.sh | bash

# Go users
go install github.com/opencode-ai/opencode@latest

Verify installation:

$ opencode --version
opencode v1.x.x

---

Step 1: Get Your API Key

1. Sign up at AIWave (GitHub, Discord, Passkey, or Email ??$5 free credit on signup)
2. Copy your API key from the dashboard
3. Note the base URL: https://aiwave.live/v1

---

Step 2: Environment Variable Configuration

OpenCode reads configuration from environment variables. Set them in your shell profile:

# ~/.bashrc or ~/.zshrc
export OPENCODE_API_BASE="https://aiwave.live/v1"
export OPENCODE_API_KEY="sk-your-aiwave-key-here"
export OPENCODE_MODEL="deepseek-v4-flash"

Reload your shell:

source ~/.bashrc

For Windows (PowerShell), add to your profile:

# In $PROFILE (run: notepad $PROFILE)
$env:OPENCODE_API_BASE = "https://aiwave.live/v1"
$env:OPENCODE_API_KEY = "sk-your-aiwave-key-here"
$env:OPENCODE_MODEL = "deepseek-v4-flash"

---

Step 3: Verify the Connection

$ opencode chat "Say 'connection successful' and nothing else"

If configured correctly, you'll see the response in your terminal. If you get an authentication error, double-check your API key and base URL.

---

Model Selection for Terminal Use

Different models serve different purposes in a terminal workflow. Here's how to configure model switching.

Default: DeepSeek V4 Flash

export OPENCODE_MODEL="deepseek-v4-flash"

Spec	Value
Input pricing	$0.14 / 1M tokens
Output pricing	$0.28 / 1M tokens
Context window	1M tokens
HumanEval	89.2%

Fast responses, massive context window, excellent coding ability. The 1M context is particularly useful in terminal ??you can pipe entire log files or source files through it.

Heavy Lifting: DeepSeek V4 Pro

# Switch for a single session
OPENCODE_MODEL="deepseek-v4-pro" opencode chat "Refactor this module to use a pub/sub pattern"

Spec	Value
Input pricing	$0.42 / 1M tokens
Output pricing	$0.84 / 1M tokens
Context window	1M tokens
HumanEval	92.1% (beats GPT-4o 90.2%)

Use it when accuracy matters more than cost.

Reasoning: DeepSeek R1

export OPENCODE_MODEL="deepseek-r1"

Spec	Value
Input pricing	$0.605 / 1M tokens
Output pricing	$2.409 / 1M tokens
Context window	128K tokens

DeepSeek R1 uses chain-of-thought reasoning. It's slower and more expensive, but produces step-by-step reasoning that's invaluable for tracking down subtle bugs.

Free Option: GLM-4.7 Flash

export OPENCODE_MODEL="glm-4.7-flash"

Spec	Value
Input pricing	$0.00 / 1M tokens
Output pricing	$0.00 / 1M tokens
Context window	128K tokens
HumanEval	72.5%

Completely free ??zero cost per token. Use it for quick lookups and simple questions.

---

Practical Usage Patterns

Pattern 1: Explain Code in Your Pipeline

# Explain a function from your codebase
grep -A 20 "def process_order" app/orders.py | opencode chat "Explain this function"

# Explain a shell command
opencode chat "Explain this command: find . -name '*.py' -exec grep -l 'import os' {} \;"

Pattern 2: Generate Shell Commands

$ opencode chat "Find all Python files modified in the last 7 days and print their sizes"
# Response: find . -name "*.py" -mtime -7 -exec ls -lh {} \; | awk '{print $5, $9}'

Pattern 3: Code Review in the Terminal

$ opencode file-review app/auth.py

Pattern 4: Generate Boilerplate

$ opencode chat "Generate a FastAPI endpoint that accepts a JSON payload with user_id (int) and action (str), validates with Pydantic, and returns a status dict"

Expected output:

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel, Field

app = FastAPI()

class ActionRequest(BaseModel):
    user_id: int = Field(..., gt=0)
    action: str = Field(..., min_length=1, max_length=100)

@app.post("/action")
async def handle_action(req: ActionRequest):
    try:
        return {"status": "ok", "user_id": req.user_id, "action": req.action}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

Pattern 5: Git Commit Messages

$ git diff --staged | opencode chat "Write a concise conventional commit message for this diff"

---

Script Wrappers for Quick Model Switching

# Add to ~/.bashrc or ~/.zshrc
oc() {
    local cmd="$1"
    shift
    case "$cmd" in
        flash)  OPENCODE_MODEL="deepseek-v4-flash" opencode "$@" ;;
        pro)    OPENCODE_MODEL="deepseek-v4-pro" opencode "$@" ;;
        reason) OPENCODE_MODEL="deepseek-r1" opencode "$@" ;;
        budget) OPENCODE_MODEL="glm-4.7-flash" opencode "$@" ;;
        coder)  OPENCODE_MODEL="qwen3-coder-480b-a35b-instruct" opencode "$@" ;;
        *)      opencode "$@" ;;
    esac
}

# Usage:
# oc flash chat "explain this regex"
# oc coder file-review main.py
# oc reason chat "find the bug in this function: ..."

---

Cost Analysis for Terminal Usage

Terminal interactions tend to be shorter than IDE chat sessions. Here's a realistic monthly estimate using AIWave pricing:

Usage Pattern	Avg Tokens (In/Out) per Call	Calls/Day	Model	Monthly Cost
Quick questions	1K / 500	20	DeepSeek V4 Flash ($0.14/$0.28)	~$0.17
Code generation	3K / 2K	10	Qwen3 Coder ($0.12/$0.36)	~$0.32
Code review	8K / 2K	5	DeepSeek V4 Pro ($0.42/$0.84)	~$0.76
Debugging	5K / 3K	3	DeepSeek R1 ($0.605/$2.409)	~$0.92
Misc lookups	??	unlimited	GLM-4.7 Flash ($0.00)	$0.00

Total: ~$2.17/month. Compare this to Cursor at $20/month or Copilot at $10/month ??that's 5? to 9? cheaper, with pay-per-use so you only pay for what you actually use.

---

Advanced: Using OpenCode with Neovim

-- In your Neovim config
vim.keymap.set('v', '<leader>oc', ':<C-u>!<CR>'
    .. 'opencode chat "Explain the selected code and suggest improvements"<CR>')

Select code in visual mode, press <leader>oc, and OpenCode opens in a terminal split with the analysis.

---

Troubleshooting

Connection timeout: AIWave servers are in Singapore. If you're in North America or Europe and see >2s latency, try GLM-4.7 Flash ($0.00/1M) for latency-sensitive tasks ??it routes through the same endpoint but responses are faster due to smaller model size.

Rate limiting: Check pricing for rate limit details by tier.

Base URL: Ensure your base URL is exactly https://aiwave.live/v1 with no trailing slash, no query params, no extra path segments.

---

Summary

• Default model: DeepSeek V4 Flash ($0.14/$0.28 per 1M tokens, 1M context)
• Complex tasks: DeepSeek V4 Pro ($0.42/$0.84, 92.1% HumanEval)
• Debugging: DeepSeek R1 ($0.605/$2.409, chain-of-thought reasoning)
• Free tier: GLM-4.7 Flash ($0.00, unlimited)
• Realistic monthly cost: ~$2 for heavy daily terminal usage

Sign up at AIWave to get $5 free credit and try it out. Explore the full model catalog ??60+ models available.