OpenCode Guide

Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed.

An open-source coding agent with a terminal UI and configurable model providers.

Coding agent · Anomaly · macOS · Windows · Linux

Suitable workflows

Developers who want to choose providers without replacing their editor.

Limitations and billing

Provider credentials, subscription eligibility and API costs differ; not every login method is interchangeable.

Capabilities we verified

Agent workflow · CLI surface · MCP · Skills · Rules / instructions · Bring your own key

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

Pricing & usage

See official pricing

Free CLI; model-provider or optional service charges. The cost of metered usage or an external agent can be separate from the subscription.

Models & access

Connect a supported provider and select its models; custom endpoints need their own configuration.

Verified families: Claude, GPT, Gemini, Grok.

Install and start the CLI

A modern terminal and a supported provider account; npm is one installation option.

npm install -g opencode-ai

Open your project folder in a terminal, then run:

opencode

Account and authentication

Run /connect to add provider credentials, then /models to select a model.

Project configuration and tools

Project configuration lives in opencode.json or opencode.jsonc; use /init to create project instructions.

First task to try

Ask for a repository overview in Plan mode, then approve a small implementation task.

Related CLI tools

All AI CLI tools →

Kilo Code CLI — A terminal coding agent with provider choice, task modes, MCP and skills.

Aider — Terminal pair programming with repository maps, editable file context and Git integration.

Pi — A minimal terminal coding agent with configurable providers, sessions and extension packages.

Project evaluation checklist

1. Open a small, familiar project and confirm that your essential language tooling works.
2. Give the agent one bounded change with an observable acceptance criterion.
3. Review the diff, run the project’s checks and compare the result with your current workflow.
4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.

Related TRAE guides

• TRAE product overview
• Trae IDE / TraeCode Download
• TraeCode Guide
• TraeWork Guide
• TRAE Pricing: TraeCode & TraeWork
• TRAE Models & Model Access
• TraeWork vs TraeCode (Trae IDE)
• Trae MCP Setup & Troubleshooting