Three-Axis Model

Omegon separates the operator's model route from provider-neutralmodel grade intent, thinking level, and context class. The concrete provider/model can change as credentials, fallbacks, or policy require, while the visible route state keeps the operator honest about what is selected and what is actually serving turns.

Three-axis routing model: model grade intent, thinking level, and context class feed into the routing engine

Axis 1: Model grade intent

Grades are provider-neutral capability bands. They are not legacy slash aliases and they are not local endpoint names. Use /model grade <F|D|C|B|A|S> to express desired capability, or/model <provider:model> to pin an exact route.

GradeUse CaseTypical Examples
F/DCheap, fast, simple lookups and boilerplatesmall hosted models, fast local models
C/BRoutine coding, execution, review, and general developmentSonnet/Codex-class routes, strong local models
A/SArchitecture, deep debugging, high-stakes reasoningfrontier reasoning and highest-grade provider routes
/model                   # Opens selector with available models
/model grade B           # Request a B-grade route, provider auto
/model provider local    # Restrict routing to local endpoints
/model policy minimum    # Allow requested grade or better

Axis 2: Thinking Level

Controls extended reasoning budget — how much reasoning effort capable providers spend before responding.

LevelUse Case
offNo extended thinking. Fastest, cheapest.
minimalBrief sanity check.
lowLight reasoning for straightforward tasks.
mediumDefault. Balanced reasoning for general work.
highDeep reasoning for architecture, debugging, multi-step problems.
/think high     # Manual override
/think off      # Disable for speed

Axis 3: Context Class

Controls context window capacity. Larger windows allow more conversation history and memory injection.

ClassWindowUse Case
Compact128k tokensQuick tasks, simple edits
Standard272k tokensStandard development work
Extended400k tokensLarge refactors, multi-file analysis
Massive1M+ tokensMassive codebases, full-project comprehension
/context massive  # Pin to maximum context
/context compact  # Minimize for cost

Orthogonality

The axes are independent. You can request grade S + off + compact (frontier model, no extra thinking, small window) or grade D + high + massive (cheap model, deep reasoning, huge context). The route controller preserves those intents without pretending they are the same thing.

Provider routing

Provider availability depends on configured credentials, endpoint health, and policy. Use/model route to inspect selected-vs-served route state, /auth status for credential diagnostics, and /model providers for the provider inventory. Local endpoints are selected with/model provider local; they are not a legacy grade.

See Providers for the authentication and fallback boundaries.