Skip to content
04 / Pricing

Pay for what
you actually use.

No per-seat tax and no mystery model routing. Solo and Pro share the standard model catalog; Team unlocks GPT-5.2 Pro, GPT-5.5 Pro, and Claude Opus 4.7. Checkpoint can stop weak PRs before they burn review credits, then the PR reviewer spends from a transparent monthly pool.

May 2026 pricing reset
Priced around real PR cost.

Current completed reviews finish fast, but stale deep runs can burn a lot of model tokens. The new tiers give bigger pools, a small free evaluation lane, and a credit gate so low-balance installs stop before another expensive run starts.

Free evaluation
100 credits
Enough to evaluate Checkpoint, chat, and a few efficient reviews without making the $10 tier unprofitable.
Critique ChatFree for all accounts

Frontier models
for everyday repo Q&A.

This product surface is separate from paid PR review: Critique Chat does not draw from the monthly review credit pool you see on model tables and plan cards below. Every signed-in user gets conversational search over connected GitHub repos — pick a model, ask in plain language, and iterate without spending those review credits. (Automated review, Remedy execution, and optional indexing still follow their own pricing.)

DeepSeekDeepSeek V4 FlashAntGroupLing 2.6 FlashMinimaxMiniMax-M2.7XiaomiMiMoMiMo v2.5 Pro+many more
Typical uses
  • Explain an error from CI with live repo search
  • Map a module you have not touched before merge
  • Sanity-check a design before you open a PR

Paid plans below are for automated PR review depth, specialist agents, and credit pools — not for chatting with your codebase.

OpenRouter
Bring your own key

$8/month harness.
Models at your cost.

Connect an OpenRouter key and Critique switches chat plus sandbox-native OpenCode PR review to your account. We run the product harness; OpenRouter bills the raw model calls directly to you.

What $8 pays for

E2B sandboxes, OpenCode orchestration, streaming chat, GitHub check runs, repository retrieval, logs, usage ledgers, and secure encrypted key handling.

What you pay OpenRouter for

The actual model tokens: lead reviewer, specialist sub-agents, chat turns, transcription, and fallback routes you choose in OpenRouter.

Why it exists

Heavy teams should not be squeezed into a low-margin $10 bundle or forced to buy an inflated credit pool just to cover vendor token variance. BYOK makes cost ownership explicit.

Connect OpenRouter key
Checkpoint

Review the submitter before
reviewing the diff.

Checkpoint is a separate pre-review gate. It checks contributor trust, PR shape, changed files, commit history, and policy overrides before the expensive review swarm starts. Run it in dry-run, warn, or block mode, then let approved PRs continue into automated review.

Spend control

Blocked PRs can skip full review so credits are reserved for code that is ready to inspect.

Governance

Modeled as its own policy, override, event log, and GitHub check run rather than a marketing-only switch.

Differentiation

Most review bots start at the diff. Critique can gate risky PRs first, then route the accepted ones through a model panel.

Credits explained

One system.
Simple rules.

Lead Model
The main reviewer. Reads the PR, synthesises all findings, writes the final verdict. On Solo and Pro you can pick any standard catalog model as the lead; Team additionally includes GPT-5.2 Pro, GPT-5.5 Pro, and Claude Opus 4.7.
Sub-Agents
Focused specialists — security, test gaps, architecture, performance. Any catalog model can play this role too, including cheaper flash models as specialists behind a heavier lead (or the reverse).
PR Depth
Tiny PRs cost less than large ones. A depth multiplier scales the total based on changed files, context size, and whether you're re-running or escalating.
Lead Model
credits
All Sub-Agents
credits
Depth Multiplier
1.0×
Total PR Cost
credits
PR SizeChanged FilesMultiplierExample: GLM-5 + 2× GLM-4.7 Flash (~4.5 base cr)
Tiny1–50.75×~3 credits
Normal6–151.0×5 credits
Large16–301.5×~7 credits
Very Large30+2.0×9 credits
Pricing
Choose a plan

Three tiers.
One philosophy.

Solo
$19/mo
billed monthly
750 credits / month
For founders and solo maintainers who need real PR review without per-seat pricing.
Checkpoint gate included
Full standard model catalog
10 reviewed repositories
Get started
ProRecommended
$49/mo
billed monthly
7-day free trial
3,000 credits / month
Best default for teams running Critique on every meaningful pull request.
Checkpoint in warn/block mode
Remedy fix proposals
50 reviewed repositories
Start free trial
Team
$149/mo
billed monthly
10,000 credits / month
For higher-volume teams that want frontier models and org-wide guardrails.
Team frontier models
Unlimited reviewed repositories
Priority review support
Sign up
Repository indexing

Full-repo embeddings
priced as slots first, credits second.

Enable a repo with Perplexity's pplx-embed-v1-4b and keep the warm snapshot current for semantic retrieval. Chat reads the newest warm snapshot, so you get hybrid search over indexed code without rebuilding context on every question.

Included slots
2 repos free
Solo adds +1 slot. Pro adds +2. Team is unlimited.
Overage enable
10 credits
Charged once when you turn on another embedded repo beyond your included slots.
Refresh cost
5 credits
Applies only to overage repos. Included-slot repos refresh for free.
Student / OSS
Unlimited free
Approved student and OSS accounts get free indexing and refreshes across every repo.
Open Source Student DealVerified students & OSS maintainers

Cleaner stack.
Student-pocket pricing.

Get the same 500 credits as the entry pool, but in a tightly curated low-cost lane: GLM-5, Kimi K2.6, and MiniMax M2.7 up top, with cheap specialist sub-agents underneath — not the full public catalog. Approved student and OSS accounts also get unlimited free repository indexing.

Lead options
Z.ai
Lead
GLM-5 + successors
Z.AI
Kimi
Lead
Kimi K2.6 + successors
MoonshotAI
Minimax
Lead
MiniMax M2.7 + successors
MiniMax
Sub-agents
Qwen
Sub-agent
Qwen 3.5 Flash
Qwen
Z.ai
Sub-agent
GLM-4.7 Flash
Z.AI
KwaiKAT
Sub-agent
KAT-Coder-Pro
KwaiPilot
Monthly
$5/mo
First month free for approved student signups.
Annual
$2.50/mo
50% off the student rate, billed as $30 / year — less than a cup of coffee nowadays.
Referral & perks
  • First month free
  • Friend gets 2 months off
  • You get month 2 refunded or month 3 free
  • Best for open-source repos, clubs, capstones, and hackathon teams, with free full-repo indexing once approved.
What 500 student credits buys
A normal review lands around 2.75–4 credits before depth scaling, depending on which lead and cheap sub-agent you pair.
Tiny
166242 PRs/mo
1–5 files · ~2.063 cr / review
Normal
125181 PRs/mo
6–15 files · ~2.754 cr / review
Large
83121 PRs/mo
16–30 files · ~4.136 cr / review
Very Large
6290 PRs/mo
30+ files · ~5.58 cr / review
Why annual wins
The yearly option cuts an already-cheap student plan in half, dropping it to $2.50/mo — less than a cup of coffee nowadays while keeping reviews running across semesters, capstones, and open-source maintenance.
Apply with student / OSS proof
EnterpriseCustom solutions

Scale with custom volume, SLAs, and deployment options. On‑prem or cloud, with dedicated support and full compliance.

Custom volume & SLAsLocal / on‑prem hostingDedicated supportSSO & compliance
Sign up
Pricing
Model credit guide

Every model.
Every cost.

These credit floors apply to automated PR review only — lead and specialist model runs that roll up into your monthly review pool on Solo, Pro, or Team. Critique Chat is separate: repo Q&A and exploration in chat use their own free lane for signed-in users and do not spend review credits. Remedy runs and repository indexing are also their own line items where we describe them above and in the FAQ.

Tier:
Solo & Pro — full catalog (sorted by credits)
$49/m
Gemma
Gemma-4-31B
Google
0.5
Lead or subSolo & Pro
DeepSeek
DeepSeek V4 Flash
DeepSeek
1
Lead or subSolo & Pro
Ling-2.6-Flash
InclusionAI
1
Lead or subSolo & Pro
Minimax
MiniMax-M2.5
MiniMax
1
Lead or subSolo & Pro
Qwen
Qwen3.6-35B-A3B
Alibaba
1
Lead or subSolo & Pro
Stepfun
StepFun-3.5 Flash
StepFun
1
Lead or subSolo & Pro
Arcee
Trinity-Large-Thinking
Arcee AI
1
Lead or subSolo & Pro
XiaomiMiMo
MiMo v2.5
Xiaomi
1.5
Lead or subSolo & Pro
Google
Gemini 3.1 Flash Lite
Google
2
Lead or subSolo & Pro
OpenAI
GPT-5.4 Nano
OpenAI
2
Lead or subSolo & Pro
KwaiKAT
KAT Coder Pro V2
KwaiPilot
2
Lead or subSolo & Pro
Minimax
MiniMax-M2.7
MiniMax
2
Lead or subSolo & Pro
Qwen
Qwen3.6 Plus
Alibaba
2
Lead or subSolo & Pro
DeepSeek
DeepSeek V4 Pro
DeepSeek
3
Lead or subSolo & Pro
Z.ai
GLM-5.1
Z.AI
3
Lead or subSolo & Pro
Z.ai
GLM-5V-Turbo
Z.AI
3
Lead or subSolo & Pro
Grok
Grok 4.3
xAI
3
Lead or subSolo & Pro
XiaomiMiMo
MiMo v2.5 Pro
Xiaomi
3
Lead or subSolo & Pro
Google
Gemini 3 Flash
Google
4
Lead or subSolo & Pro
Kimi
Kimi K2.6
MoonshotAI
4
Lead or subSolo & Pro
Qwen
Qwen3.5-397B-A17B
Alibaba
5
Lead or subSolo & Pro
OpenAI
GPT-5.4 Mini
OpenAI
6
Lead or subSolo & Pro
Qwen
Qwen3.6-Max-Preview
Alibaba
8
Lead or subSolo & Pro
Google
Gemini 3.1 Pro
Google
16
Lead or subSolo & Pro
OpenAI
GPT-5.3 Codex
OpenAI
18
Lead or subSolo & Pro
OpenAI
GPT-5.4
OpenAI
20
Lead or subSolo & Pro
Claude
Claude Sonnet 4.6
Anthropic
22
Lead or subSolo & Pro
OpenAI
GPT-5.5
OpenAI
40
Lead or subSolo & Pro
Team — frontier add-ons (GPT-5.2 Pro, GPT-5.5 Pro, Claude Opus 4.7)
Claude
Claude Opus 4.7
Anthropic
37
TeamTeam
OpenAI
GPT-5.2 Pro
OpenAI
180
TeamTeam
OpenAI
GPT-5.5 Pro
OpenAI
237
TeamTeam

Credits are calculated per review unit — approximately 1M input + 150k output tokens for the lead model on a normal PR. This table does not describe Critique Chat pricing; chat stays outside the review credit meter.

Pricing
How far do your credits go?

Pick your stack.
See the math.

Estimates below are for PR review credit burn, not Critique Chat. Use Lead then Sub-agent on one list (teal vs green), tweak sub count and depth, and see how each plan's pool stretches.

LeadSub

Tap a row to set the lead reviewer, then switch to Sub-agent for the specialist model.

Sub-agents
PR size / depth
Estimated cost(0.5 lead + 1 × 1 sub) × 1×
2 credits / PR
Solo
$19/mo
375
PR reviews / month
750 credits ÷ 2 credits
Pro
$49/mo
1,500
PR reviews / month
3,000 credits ÷ 2 credits
Team
$149/mo
5,000
PR reviews / month
10,000 credits ÷ 2 credits
Pricing FAQ

Questions we hear
before you upgrade.

Credits apply to automated review and to Remedy runs inside Critique — not to everyday Critique Chat. Third-party coding assistants bill their vendors directly.

Plans & credits

One credit is our normalized unit for a standard review slice — roughly 1M input tokens and 150k 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.

Solo and Pro share the same standard model lineup and the same flexibility: any listed standard model can be your lead reviewer or a specialist sub-agent, interchangeably. Team adds GPT-5.2 Pro, GPT-5.5 Pro, and Claude Opus 4.7 plus a much larger monthly pool. The internal plan keys are standard, pro, and ultra, but the customer-facing tiers are Solo, Pro, and Team.

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. Solo and Team follow the CTAs shown there as well.

BYOK is the harness plan for teams that already want OpenRouter to bill tokens directly. Critique charges $8/month for orchestration — sandboxes, OpenCode review runs, chat streaming, GitHub checks, repository retrieval, usage ledgers, and the account control plane. Your model spend stays in your OpenRouter account instead of being bundled into Critique credits.

Chat, Remedy & other agents

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.

Contact

Write to support@critique.sh for billing, accounts, and general product help. We read every message.

Ready to ship better code?

Start with the clearest path.

Create an account to use Critique Chat and connect the GitHub App when your team is ready. Upgrade or change plans from settings anytime.