Pay for what
you actually use.

One credit is our normalized unit for a standard review slice — roughly 100k input tokens and 15k output tokens on the lead model for a normal-sized PR. Specialist sub-agents add their own credit cost on top, and the depth multiplier scales everything for tiny vs very large changes. A single full review is often about 3–50+ credits depending on models and PR size. Your monthly pool is meant to cover many reviews, not to map one-to-one with a raw “job” counter.

Standard and Pro share the same full model lineup and the same flexibility: any listed model can be your lead reviewer or a specialist sub-agent, interchangeably. Ultra adds GPT-5.2 Pro, GPT-5.4 Pro, and Claude Opus 4.7 (frontier credits) and a much larger monthly pool. The only catalog split is those Ultra-only models; lead vs sub is never a separate “tier” of models.

Upgrades apply right away so you are not stuck on a smaller pool when volume spikes. Downgrades take effect at the start of your next billing cycle so you keep the features you already paid for through the end of the current period.

No. Monthly credits reset at each billing boundary. We surface costs transparently so teams can right-size plans instead of banking opaque rollover balances.

Pro is advertised with a 7-day trial where that offer is active — see the plan cards above for the exact label on your signup path. Standard and Ultra follow the CTAs shown there as well.

No. Critique Chat is conversational Q&A against connected GitHub repos with frontier models, and it does not draw down the same monthly pool that meters automated PR review. You can explore branches, compare approaches, and ask follow-ups in chat without spending review credits. Repository indexing has its own rules (slots and refresh costs) where applicable — chat itself stays outside the review credit meter.

Remedy is not the chat message — it is the coding agent that edits files, runs managed execution steps, and can trigger follow-up verification passes. That work bills through Critique credits because our stack is carrying the model runs and apply loop end-to-end. The conversation that suggested the fix may be in free chat; turning it into real commits, patches, and checks is what crosses into metered automation.

Those tools bill you through their vendors, not through Critique. GitHub Copilot is billed by Microsoft / GitHub, Codex usage goes through OpenAI, and Claude Code sits with Anthropic under their terms. We do not resell or bundle those subscriptions. If you export a blueprint or plan from Critique and run it entirely inside your own agent or IDE, any token or seat charges from those products stay between you and that provider.

Yes — many teams use Critique for review and hand execution to Copilot, Codex, Claude Code, or an internal runner. In that split, Critique credits cover automated review (and optional Remedy only if you choose it inside Critique), while execution spend stays with whichever agent vendor you already pay. You are never forced to run fixes through our hosted agent to get value from review.

Indexing is priced separately from review credits: included repo slots, one-time overage enablement, and refresh rules are summarized in the embeddings section above. Student and OSS approvals can include unlimited indexing — check that block for the latest copy. Chat reads warm snapshots once a repo is embedded, but the embedding lifecycle is not the same line item as per-PR review credits.