Spend smart: OpenCode Zen & the free tier

🎯Goal. Skip managing your own provider key by using opencode's hosted models — starting with a genuinely free tier — and put guardrails on your spend.

1. 1Don't want to wire up your own key? Use OpenCode Zen, opencode's hosted model service. It's pay-as-you-go, billed per 1M tokens — there's no flat monthly plan.
2. 2Zen includes a free tier of five models (Big Pickle, DeepSeek V4 Flash Free, MiMo-V2.5 Free, North Mini Code Free, Nemotron 3 Ultra Free) — enough to try opencode without spending anything. Paid models range from DeepSeek V4 Flash at $0.14 in / $0.28 out per 1M tokens up to Claude Fable 5 at $10.00 in / $50.00 out (Claude Opus models ~$5.00 in / $25.00 out).
3. 3Set guardrails: auto-reload tops up by a default $20 when your balance drops below $5, and you can set per-workspace / per-member monthly usage limits. (Card processing adds 4.4% + $0.30 per transaction; team plans are free during beta.)

✓You'll see. opencode running on a hosted Zen model — free-tier to start — with auto-reload and monthly limits keeping your spend predictable.

💳Cost. Zen is pay-as-you-go per 1M tokens with a free five-model tier; paid models span $0.14/$0.28 to $10/$50 per 1M tokens. Auto-reload and per-member limits keep costs in check.

💡Takeaway. OpenCode Zen is the zero-setup path: start free, scale to paid models only as you need them, and cap spend with built-in limits.