27 models across four surfaces. Filter by job-to-be-done, assemble a lead + specialist + Remedy stack, and understand real credit costs before you ship.
Want one answer
GLM-5-Turbo + MiMo V2 Pro
Balanced default stack
Cost-sensitive
MiMo V2 Flash
or Qwen3.6 Plus
Quality over speed
GPT-5.4
or Claude Sonnet 4.6
Remedy defaults
MiMo V2 Pro
Free chat: Qwen3.6 Plus
What are you optimizing for?
Balanced quality and cost for most engineering teams — Best starting point for most teams. Strong lead + reliable Remedy.
Pre-configured lead + specialist + Remedy combinations. Start with a preset, not a blank slate.
Where most teams should start
Startup teams, balanced engineering orgs
Maximum coverage per credit spent
High-volume orgs, cost-sensitive pipelines
Strong defaults with escalation path
Mid-size engineering teams, mixed PR sizes
Standard stack + Ultra when it matters
Frontier-only teams, high-stakes codebases
Built for automated fix execution
Teams shipping Remedy as a core workflow
27 models
Z.AI
Credit floor
3crSpeed
FastContext
203KBest for: agent orchestration, long execution chains, stable tool use
Xiaomi
Credit floor
3crSpeed
BalancedContext
1MBest for: Remedy execution, agent adaptability, 1M context
Anthropic
Credit floor
22crSpeed
BalancedContext
1MBest for: coding, codebase navigation, agents
OpenAI
Credit floor
20crSpeed
BalancedContext
1MBest for: coding, tool use, long-context reasoning
Alibaba
Credit floor
2crSpeed
BalancedContext
1MBest for: repo-scale problem solving, coding, deep sub-agent work
Credit floor
0.5crSpeed
FastContext
262KBest for: broad low-cost coverage, document understanding, coding checks
Xiaomi
Credit floor
0.5crSpeed
InstantContext
262KBest for: reasoning at low cost, coding, agent loops
StepFun
Credit floor
1crSpeed
InstantContext
262KBest for: quick review passes, chat-like responsiveness, fast PR checks
KwaiPilot
Credit floor
1crSpeed
FastContext
256KBest for: enterprise software tasks, coding-focused review, specialist work
MiniMax
Credit floor
1crSpeed
FastContext
197KBest for: general productivity, coding, efficient coverage
MiniMax
Credit floor
2crSpeed
BalancedContext
197KBest for: autonomous productivity, debugging, Remedy execution
Credit floor
2crSpeed
InstantContext
1MBest for: high-volume tasks, broad coverage at minimal cost, fast sub-agent
OpenAI
Credit floor
2crSpeed
InstantContext
400KBest for: extraction, ranking, lightweight sub-agent work
Alibaba
Credit floor
2crSpeed
FastContext
262KBest for: balanced quality, fast responses, coding checks
DeepSeek
Credit floor
2crSpeed
BalancedContext
164KBest for: harder review tasks, Remedy execution, value reasoning
MoonshotAI
Credit floor
3crSpeed
BalancedContext
262KBest for: multimodal review, agentic tasks, visual coding
Z.AI
Credit floor
4crSpeed
BalancedContext
203KBest for: long-horizon coding, extended autonomous work, complex review
Credit floor
4crSpeed
FastContext
1MBest for: near-Pro quality at lower latency, broad coverage, fast thinking
Alibaba
Credit floor
5crSpeed
BalancedContext
262KBest for: stronger reasoning, code review, GUI tasks
OpenAI
Credit floor
6crSpeed
FastContext
400KBest for: balanced capability + latency, general-purpose review, cost-aware teams
xAI
Credit floor
8crSpeed
FastContext
2MBest for: fast flagship tasks, large context, strong tool-calling
OpenAI
Credit floor
14crSpeed
DeepContext
400KBest for: long-running agentic coding, high-context software tasks, complex Remedy
Credit floor
16crSpeed
DeepContext
1MBest for: complex engineering, multimodal workflows, frontier reasoning
OpenAI
Credit floor
18crSpeed
DeepContext
400KBest for: terminal-heavy tasks, SWE-style work, advanced coding review
Anthropic
Credit floor
37crSpeed
DeepContext
1MBest for: large codebases, hard refactors, multi-step debugging
OpenAI
Credit floor
180crSpeed
DeepContext
400KBest for: high-stakes reasoning, coding at max depth, frontier analysis
OpenAI
Credit floor
237crSpeed
DeepContext
1MBest for: maximum OpenAI capability, complex system design review, frontier coding
The credit floor shows the minimum model cost lane. Actual review and Remedy spend depends on lead + specialist + depth multiplier. Remedy adds execution overhead including possible loop 2 re-review.
See full pricing and credit examplesDeepSeek + MiMo Flash
GLM-5-Turbo lead + Qwen specialist
Claude Sonnet + GPT-5.4
MiMo V2 Pro or GPT-5.1 Codex Max
Critique Chat is free for signed-in users and does not spend PR review credits. The 8 chat models are separate from the main review and Remedy catalog.
By default, Critique selects models based on PR size, plan, and depth requirements. Power users and enterprise teams can pin specific models for lead, specialist, and Remedy roles.
If a model is unavailable or rate-limited, Critique falls back to the next appropriate model in the same cost tier. Ultra models do not fall back to Standard without explicit configuration.
Standard and Pro plans access the full catalog except Ultra-only models. Ultra plan unlocks Claude Opus 4.6, GPT-5.2 Pro, and GPT-5.4 Pro.
Raw OpenRouter IDs are shown in each expanded model card. They are secondary on this page but primary in API and admin contexts. Critique normalizes aliases automatically.
Use raw IDs when configuring CI workflows, calling the API directly, or pinning a specific model version. The dashboard UI uses display names.
Credits are a normalized billing unit. 1 credit maps to a defined compute allocation. A full review cost is lead + specialist + any Remedy execution overhead, not just the floor.
GLM-5-Turbo as lead, Qwen3.5-27B as specialist, MiMo V2 Pro for Remedy. Change any layer when you have data to justify it.