Starter
$15prepaid
100 cloud stages
A clean cloud balance for the runs that need a separate machine. Local reviews remain included.
- Independent cloud finish runs
- Proof artifacts + history
- Local CLI stages included
CLI pricing · no seats
Local is included.
Cloud is 15¢ a stage.
Critique's pinned reviewer runtime is included locally. Cloud adds a 15¢ execution fee per stage when you need a separate clean machine; managed model usage stays visible.
LOCAL RUNS INCLUDEDMODEL COST STAYS VISIBLECLOUD ONLY WHEN CHOSEN
/ 01 — Cloud balancePay for the
Pay for the
remote machine.
Cloud stages are shared across your account at fifteen cents each. Local execution does not consume this balance.
Builder
RECOMMENDED$75prepaid
500 cloud stages
For agents that finish work continuously across local branches, cloud sandboxes, and CI.
- Shared cloud balance
- Machine keys + CI use
- Unlimited local execution stages
Team
$300prepaid
2,000 cloud stages
A shared meter for teams making Critique part of their shipping contract.
- Shared policies + hooks
- Cloud CI and agent integrations
- Priority support
04Your runtime
Model cost
BYO provider
Run locally through Critique's pinned reviewer runtime, use managed Critique inference, or choose a clean cloud machine. Critique never hides model spend inside the check price.
- Local credentials remain with their official runtime
- Managed model usage stays separate from check packs
Cloud stage packs cover Critique orchestration. Local stages are included. Model usage is always shown and billed independently by the selected runtime or provider.
/ 02 — The receiptNo hidden
No hidden
model markup.
A receipt separates execution location, Critique's cloud fee, input/output tokens, and model cost. A costly model never disappears behind a cheap-looking stage price.
Read the finish contract01Local / cloud stage$0 / 15¢
+02Selected modelprovider cost
=03Run receiptvisible first
/ 03 — Choose the runtimeKeep model spend
Keep model spend
in the open.
Use the runtime you already trust. Local execution is included; cloud orchestration and model usage remain visible as separate lines.
RuntimeModel accessCritique feeModel bill
01Local Critique runtime
Pinned reviewer runtimeIncludedProvider or Critique credits02Managed local inference
Critique model catalogIncludedSeparate model usage03Critique Cloud
A managed Critique runtime15¢Separate managed charge/ 04 — Managed model shelfThe current
The current
model catalog.
37 models are available as managed runtime choices. Accounts with review credits see this same shelf in hosted sessions; CritiqueCode hosted routes are listed in the app.
ModelProviderAccessCredit floor
01StepFun-3.7 Flash
StepFunManaged credits1 cr02KAT Coder Pro v2.5
KwaiPilotManaged credits2 cr03Nemotron 3 Ultra
NVIDIAManaged credits3 cr04Trinity-Large-Thinking
Arcee AIManaged credits1 cr05Hy4 Preview
TencentManaged credits1 cr06DeepSeek V4 Flash 0731
DeepSeekManaged credits0.5 cr07DeepSeek V4 Flash Vision Exp
DeepSeekManaged credits1 cr08MiniMax-M3
MiniMaxManaged credits3 cr09Gemini 3.5 Flash Lite
GoogleManaged credits2 cr10GPT-5.6 Luna
OpenAIManaged credits4 cr11Qwen3.7 Plus
AlibabaManaged credits1.5 cr12Qwen3.8 Flash
AlibabaManaged credits0.5 cr13DeepSeek V4 Pro 0813
DeepSeekManaged credits1 cr14Seed 2.0 Code
ByteDance SeedManaged credits2 cr15Qwen3.8 2.4T A95B
AlibabaManaged credits6 cr16Muse Glimmer 30B
MetaManaged credits0.5 cr17Qwen3.8 27B
AlibabaManaged credits1 cr18GLM-5.3
Z.AIManaged credits3 cr19GLM-5.3 Flash
Z.AIManaged credits1 cr20Kimi K2.6
MoonshotAIManaged credits4 cr21Kimi K2.7 Code
MoonshotAIManaged credits4.5 cr22Kimi K3
MoonshotAIManaged credits20 cr23MiMo v2.5 Pro
XiaomiManaged credits1 cr24Gemini 3.8 Flash
GoogleManaged credits4 cr25Qwen3.8-Max
AlibabaManaged credits6 cr26Grok Build 0.1
xAIManaged credits3 cr27Grok 4.6
xAIManaged credits6 cr28Gemini 3.1 Pro
GoogleManaged credits16 cr29Claude Sonnet 5
AnthropicManaged credits15 cr30Claude Opus 5
AnthropicManaged credits30 cr31Claude Fable 5.1
AnthropicManaged credits60 cr32GPT-5.6 Terra
OpenAIManaged credits20 cr33GPT-5.6 Sol
OpenAIManaged credits40 cr34Fugu Ultra
SakanaManaged credits40 cr35Mercury 2.5 Preview
InceptionManaged credits1 cr36Muse Spark 1.3
MetaManaged credits20 cr37GPT-5.6 Sol Pro
OpenAIManaged credits55 cr/ 05 — The fine printStraight
Straight
answers.
01What is a Critique check?+
One cloud check is one Critique execution stage: the remote isolated workspace, change capsule, independent agent contract, and proof artifact. Cloud stages cost $0.15. Local Critique reviewer stages are included.
02Does the cloud 15¢ include the model?+
No. The 15¢ is the Critique Cloud execution fee. Managed cloud model usage is a separate charge. Local Critique stages have no execution fee; when you are signed in, model tokens bill your Critique credit balance via the Inference API. Otherwise the model provider you configure bills usage directly.
03Does Critique reread my whole codebase for every change?+
Critique starts with the task and the exact work in progress, then follows nearby code and tests when they matter. Local review stays in a separate workspace on your machine. When you explicitly choose cloud, Critique uploads the protected current working tree—including uncommitted changes—and gives each critic, repairer, and verifier a fresh full-repository workspace.
04Why not charge per seat?+
Coding agents change the unit of work. A team with three developers can generate more candidate changes than a team of thirty. Critique prices the independent finish pass, not the number of humans who happen to be on the account.
05What happens when a repair is applied?+
Critique can run a critic, a bounded repair, and a fresh independent verifier. Local stages are included. Each cloud stage is 15¢, and managed model usage is billed separately. The receipt records execution, tokens, and model cost independently.
LOCAL INCLUDED · CLOUD + MODEL COST SEPARATECheck the change