Best API & Subscription for Oh My Pi

omp's intent routing (default/smol/slow/plan) pairs well with a cheap-model plan for the smol slot. OpenCode Go covers the open-weight tiers cheaply; Standard Compute is the unlimited option for its heavier default/plan slots when you run it all day. Declare either in models.yml.

Plan facts verified 2026-07-17
Cheapest tokens

OpenCode Go for the smol/default slots — its model variety suits omp's routing.

If you need unlimited / always-on

Standard Compute for the plan/default slots on always-on use — no window to exhaust mid-task.

Every option for omp, compared honestly

OptionPriceThe honest take
OpenCode Go$10/mo ($5 first month)Best raw open-weight value: ~$60/mo of usage for $10 (~6x). Capped by $12/5h + $30/week windows. Works with any agent.
Standard ComputeUNLIMITED$9 / $39 / $99 / $399Unlimited: no token meter, no 5-hour or weekly windows — and unlike the open-weight-only plans here, smart routing reaches the full frontier (Claude, GPT, Gemini class). Extreme sustained load is paced smoothly, not cut off. Wins when your agent runs all day or needs frontier quality that capped open-weight plans can't match.
OpenRouterPay-as-you-go400+ models, ~5.5% fee, no markup on inference. Maximum flexibility, not a subscription — bill scales with usage, so heavy agents get expensive.
GLM Coding Plan (Z.ai)$18 / $72 / $160GLM-5.2-only on prompt-count windows. Good if GLM quality covers you; quota burns 2-3x faster at peak.

Competitor prices from their public pages as of 2026-07-17. Spot an error? tell us — accuracy is the point.

Disclosure: this guide is maintained by Standard Compute. We're one option among many above — genuinely the best fit only when your omp runs heavy or always-on and the capped plans would stop it. For light or predictable use, the value multipliers above are often cheaper, and we say so.

2-min omp setup →All flat-rate plans compared →The cheapest-tokens math →