OpenCode CLI Setup
Learn how to configure OpenCode CLI to use Aiberm’s API. This guide covers installation and configuration for Windows, macOS, and Linux.
What is OpenCode?
OpenCode is a Go-based open-source command-line programming tool (CLI) that provides powerful AI assistance for developers. It offers an intuitive Terminal User Interface (TUI) and supports multiple LLM providers including OpenAI, Anthropic, Gemini, and more.
By integrating OpenCode with Aiberm API, you can access any model available on Aiberm (including Claude, GPT, Gemini, and more) through a unified interface with one key and one base URL.
Prerequisites
Before you begin, ensure you have:
- An Aiberm account (Sign up here)
- An Aiberm API key (Get your key)
- Terminal/Command Prompt access on your computer
Terminal Emulator
OpenCode requires a modern terminal emulator. Recommended options:
- WezTerm (cross-platform)
- Alacritty (cross-platform)
- Ghostty (Linux and macOS)
- Kitty (Linux and macOS)
Windows users can also use PowerShell or Windows Terminal. macOS users can use the built-in Terminal.app or iTerm2. Linux users can use the built-in terminal or GNOME Terminal, Konsole, etc.
Installation
Choose your operating system below for installation instructions.
macOS & Linux
The easiest way is through the install script:
curl -fsSL https://opencode.ai/install | bash
Or using Homebrew:
brew install anomalyco/tap/opencode
Verify installation:
opencode --version
Windows
Windows users should first install Node.js, then install via NPM:
npm i -g opencode-ai@latest
Or using Chocolatey:
choco install opencode
Or using Scoop:
scoop bucket add extras
scoop install extras/opencode
Verify installation:
opencode --version
If you prefer a graphical interface, OpenCode also offers a desktop app available at OpenCode Download Page.
Configuration
Step 1: Initialize Provider
After installation, run the following command in your terminal before launching OpenCode:
opencode auth login
- In the provider list, select other (at the bottom, you can search for it)
- Enter Provider ID: type
aiberm - Enter API Key token: you can enter any value (e.g.,
admin), the actual key is referenced via config file
This step registers a custom provider in OpenCode’s local credential manager.
Step 2: Edit Config File
Open the OpenCode config directory:
Windows:
Press Win + R, paste the following, then press Enter:
%userprofile%\.config\opencode
macOS / Linux:
In terminal, run:
cd ~/.config/opencode
Or access ~/.config/opencode/ in Finder/file manager.
Create or edit opencode.json in this directory. Below is an example configuration with Claude models:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"aiberm": {
"npm": "@ai-sdk/anthropic",
"name": "Aiberm",
"options": {
"baseURL": "https://aiberm.com/v1",
"apiKey": "sk-your-aiberm-api-key"
},
"models": {
"claude-opus-4-5-20251101": {
"name": "Claude-4.5-Opus"
},
"claude-sonnet-4-5-20250929": {
"name": "Claude-4.5-Sonnet"
},
"claude-haiku-4-5-20251001": {
"name": "Claude-4.5-Haiku"
}
}
}
}
}
You can also add other models available on Aiberm. For example, to add OpenAI GPT models:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"aiberm": {
"npm": "@ai-sdk/openai",
"name": "Aiberm",
"options": {
"baseURL": "https://aiberm.com/v1",
"apiKey": "sk-your-aiberm-api-key"
},
"models": {
"openai/gpt-4.1": {
"name": "GPT-4.1"
},
"openai/gpt-4.1-mini": {
"name": "GPT-4.1 Mini"
},
"openai/gpt-4.1-nano": {
"name": "GPT-4.1 Nano"
},
"openai/gpt-4o": {
"name": "GPT-4o"
},
"openai/gpt-4o-mini": {
"name": "GPT-4o Mini"
}
}
}
}
}
Check the Models List page or Aiberm Pricing for all available models on Aiberm.
Important:
- Replace
"sk-your-aiberm-api-key"with your actual API Key from Aiberm Console - JSON format is sensitive to symbols
Verify Configuration
After saving the config file, restart your terminal, then navigate to your working directory:
cd your-working-directory
Launch OpenCode:
opencode
In the chat interface, enter the command:
/models
You should see Aiberm and its models in the model list. Select one and you’re ready to go!
Switching Models
In the OpenCode interface, enter the /models command, then select your desired model from the list.
Example models available through Aiberm:
- anthropic/claude-sonnet-4-5-20250514: Anthropic’s Claude 4.5 Sonnet
- anthropic/claude-opus-4-20250514: Anthropic’s Claude 4 Opus
- openai/gpt-4.1: OpenAI’s GPT-4.1
- openai/gpt-4o-mini: OpenAI’s GPT-4o Mini
- google/gemini-3-pro: Google’s Gemini 3 Pro
- And more…
Visit Aiberm Pricing for the complete list of available models.
Troubleshooting
Config Changes Not Taking Effect
- Restart OpenCode
- Check
opencode.jsonsyntax (JSON format) - Verify config file path is correct
401/403 Errors
- 401 error: API Key not set or invalid
- 403 error: Insufficient permissions or expired key
- Check the
apiKeyin your config file - Verify your API key at Aiberm Console
OpenCode Not Found
macOS/Linux:
# Check if OpenCode is in your PATH
which opencode
# If not found, try reinstalling:
curl -fsSL https://opencode.ai/install | bash
Windows:
- Verify Node.js is installed correctly
- Try reinstalling via npm:
npm i -g opencode-ai@latest
Config File Location
The opencode.json config file should be placed at:
- Windows:
C:\Users\{username}\.config\opencode\opencode.json - macOS / Linux:
~/.config/opencode/opencode.json
Notes
- Run OpenCode in a dedicated project folder. Avoid running it in sensitive directories (such as system folders or directories containing credentials). OpenCode operates starting from the current working directory.
- OpenCode uses JSON format config files. Ensure your config file syntax is correct. You can use online JSON validators to check the format.
- OpenCode only reads file content when you explicitly authorize it. It’s recommended to use it in a dedicated project folder.
- Chinese input and output are fully supported.