Skip to main content
Every Check Run Agent runs on a model you choose in its front matter. This page covers the available models, how reasoning and effort behave, per-model pricing, and how to keep costs down.

​
Choosing a Model

Set model: in your front matter to choose which model powers the agent. The default model is claude-opus-4-6.
If you omit model:, the agent uses the default (claude-opus-4-6). If you set model: to a value Macroscope doesn’t recognize (or a deprecated one), the check run concludes NEUTRAL with a “model is not available on Macroscope” message — it does not fall back to a default.
ModelReasoningEffortNotes
Anthropic
claude-opus-4-5low (default), medium, highlow (default), medium, highEarlier Opus generation. Smaller context window — best for short, targeted checks.
claude-opus-4-6 (default)autolow (default), medium, highStrongest general-purpose option. Large context window.
claude-opus-4-7autolow (default), medium, highLarge context window.
claude-opus-4-8autolow (default), medium, highLatest Opus. Large context window.
claude-sonnet-4-5low (default), medium, highlow (default), medium, highFaster than Opus. Smaller context window.
claude-sonnet-4-6autolow (default), medium, highFaster than Opus, with a large context window.
claude-sonnet-5autolow (default), medium, highLatest Sonnet. Faster than Opus, with a large context window.
claude-fable-5autolow (default), medium, highHighest intelligence. Best for hard tasks.
OpenAI
gpt-5-2low (default), medium, high—Earlier GPT generation.
gpt-5-4low (default), medium, high—More capable than 5.2.
gpt-5-5low (default), medium, high—Previous flagship GPT.
gpt-5-6-sollow (default), medium, high—Latest GPT. Frontier tier — highest quality.
gpt-5-6-terralow (default), medium, high—Balanced price and quality.
gpt-5-6-lunalow (default), medium, high—Cost-optimized.
Open source (Beta)
kimi-k2-7-codealways on—
glm-5-2off, high (default), xhigh—Large context window.
minimax-m3on by default; set off to disable—Large context window.
qwen-3-7-pluson by default; set off to disable—Smaller context window.
  • Default = the value used when the field is omitted from front matter.
  • Effort applies to Anthropic models only — GPT and open-source models ignore it (shown as —).
  • Newer Anthropic models (Opus 4.6 / 4.7 / 4.8, Sonnet 4.6 / 5, Fable 5) set thinking automatically, so their reasoning field is ignored (shown as auto).
  • xhigh is only supported by glm-5-2.
Open source models are in beta and served through a limited set of inference providers (e.g. Fireworks AI). While we expand the number of inference providers we support, capacity fluctuations from these providers (during heavy load times) mean that latency may occasionally be higher due to request queuing.

​
Reasoning and Effort

  • reasoning accepts off | low | medium | high | xhigh
  • effort accepts low | medium | high
Which field applies depends on the model:
  • Anthropic — effort always applies. claude-opus-4-5 and claude-sonnet-4-5 additionally honor reasoning, which maps to extended thinking; newer Anthropic models set thinking automatically and ignore reasoning.
  • OpenAI and open source — reasoning selects the thinking level; effort is ignored.
xhigh is supported only by glm-5-2. On any other model the run falls back to low and surfaces a warning on the check run details page. For example: 
---
title: Security Review
model: claude-opus-4-5
reasoning: high
effort: medium
---

Your instructions here.

​
Pricing

Check Run Agents bill in credits based on the underlying model’s token cost. Rates below are USD per 1M tokens. claude-opus-4-6 is the default when no model is set.
ModelInputOutputCached input
Anthropic
claude-opus-4-5$5.00$25.00$0.50
claude-opus-4-6 (default)$5.00$25.00$0.50
claude-opus-4-7$5.00$25.00$0.50
claude-opus-4-8$5.00$25.00$0.50
claude-sonnet-4-5$3.00$15.00$0.30
claude-sonnet-4-6$3.00$15.00$0.30
claude-sonnet-5$2.00$10.00$0.20
claude-fable-5$10.00$50.00$1.00
OpenAI
gpt-5-2$1.75$14.00$0.18
gpt-5-4$2.50$15.00$0.25
gpt-5-5$5.00$30.00$0.50
gpt-5-6-sol$5.00$30.00$0.50
gpt-5-6-terra$2.50$15.00$0.25
gpt-5-6-luna$1.00$6.00$0.10
Open source (Beta)
kimi-k2-7-code$0.95$4.00$0.19
glm-5-2$1.40$4.40$0.14
minimax-m3$0.30$1.20$0.06
qwen-3-7-plus$0.40$1.60$0.08
All prices are USD per 1M tokens. Agent usage is billed in credits: raw model cost + 5% markup, then ÷ $0.01 per credit (1 credit = $0.01). claude-sonnet-5 shows introductory pricing through Aug 31, 2026 (standard afterward: $3.00 / $15.00 / $0.30 per 1M).

​
Managing Costs

To keep costs down: use include/exclude or .macroscope/ignore.md to scope to relevant files, prefer full_diff over code_object, and use lower effort for simple checks. Cost information is available in two places:
  • Settings → Billing — Admins can see a full cost breakdown across all Check Run Agents.
  • GitHub Check Run details page — Shows the billed total for each individual run.