How does OpenCode choose a model?

OpenCode reads its config from ~/.config/opencode/opencode.json. Each provider block names a provider, its models, and the API key source. You can mark a default model and override it per session with a slash command. There is no hidden router deciding for you — the model used is the one you named, which makes costs predictable.

How do you set a cheap default?

Start cheap and escalate on purpose:

1. Set a small, fast model as default — something in the Haiku or GPT-mini class.
2. Keep one frontier model configured for planning and hard debugging.
3. Switch mid-session when a task stalls: /model anthropic/claude-sonnet.
4. Add a local model as offline fallback for trivial edits.

The pattern that saves the most money is planning cheap first. Let the small model attempt the change. Escalate only when tests fail twice.

How much can you actually save?

A typical day of light coding uses 200k-500k tokens. Run entirely on a frontier model that is $2-$6. Mix in a cheap default for the 70% of turns that are reads, searches, and small edits, and the same day lands closer to $0.80-$2.00. That is a 60-70% cut for work that rarely needed the big model.

Should you run models locally?

For autocomplete-like edits and commit messages, a local 7B-14B model on a modern laptop is fine and free. For repo-wide refactors it is frustrating: small models lose context and invent file paths. Keep local as the fallback, not the primary. If you already run droid on your own keys, the same key file can serve both tools.

What breaks?

Two gotchas. First, model names change often — a stale config silently fails or falls back. Second, mixing providers means mixing context limits; a 128k-context plan does not fit in a 32k local model. Pin explicit context windows in config so a large file does not blow the request size limit mid-task.

Quick Summary

• OpenCode config lives at ~/.config/opencode/opencode.json.
• Set a cheap small model as default, keep a frontier model for planning.
• Mixing models can cut a day’s spend from ~$2-$6 to ~$0.80-$2.00.
• Local models work for trivial edits but fail on repo-wide work.
• Pin context limits — provider switching can break large tasks.

Last updated September 2026.

What is OpenCode?

OpenCode is a text-based coding agent maintained in the open on GitHub. Unlike IDE plugins, it is provider-neutral: it talks to Anthropic, OpenAI, Google, or a local model through a config file. It reads your project tree, proposes diffs, and runs shell commands with your consent. That neutrality is the main reason developers pick it over lock-in tools.

How do you install OpenCode?

Two supported routes:

• Install script: curl -fsSL https://opencode.ai/install | bash
• Package managers: npm i -g opencode-ai, or Homebrew on macOS with brew install opencode

After install, run opencode auth login and pick your provider. The key is stored locally under ~/.local/share/opencode. No account is required to use your own API key.

How do you complete your first task?

Change into a repo and launch the agent:

1. cd ~/projects/my-api
2. opencode
3. Type a concrete request: “Add a /health endpoint that returns 200 with a JSON body containing uptime.”
4. Review the diff it shows, then approve with y.

OpenCode edits only after you confirm, so the worst case is a rejected patch, not a wrecked working tree. If the plan looks off, reply with a correction instead of starting over — it keeps the context.

Is OpenCode free?

The tool is free and open source. You pay for whichever model you connect. With a cheap model a small task runs a few thousand tokens, well under $0.05. With a frontier model the same task may cost $0.20-$0.50. There is no per-seat license and no usage cap imposed by OpenCode itself.

OpenCode vs IDE agents

If you want autocomplete and inline hints, an editor plugin wins. OpenCode targets the opposite workflow: give an agent a goal and let it touch many files. It pairs well with droid, which leans more autonomous, while OpenCode stays easier to script and embed in pipelines.

Quick Summary

• OpenCode is a free, open-source terminal coding agent.
• Install via curl -fsSL https://opencode.ai/install | bash or npm i -g opencode-ai.
• It is provider-neutral — bring any API key, no account needed.
• First task takes about 5 minutes; it always asks before editing.
• Best for developers who want a scriptable agent, not autocomplete.

Last updated September 2026.