메뉴
Route Claude API calls to the right tier — Haiku for structured/fast tasks, Sonnet for reasoning. Use when building any Python app or Claude Code tool that makes multiple Claude API calls and you want to cut cost without losing quality.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | tier-router |
| description | Route Claude API calls to the right tier — Haiku for structured/fast tasks, Sonnet for reasoning. Use when building any Python app or Claude Code tool that makes multiple Claude API calls and you want to cut cost without losing quality. |
A two-tier routing pattern for Claude API calls. Default for 80% of calls is Haiku — fast, cheap, and sufficient for structured work. Escalate to Sonnet only when the task needs real reasoning.
FAST (Haiku) — use by default:
DEEP (Sonnet) — use only when:
When in doubt, start with FAST and only escalate if the output is visibly worse.
| Model | $/1M input | $/1M output | Relative cost |
|---|---|---|---|
| Haiku 4.5 | $0.80 | $4.00 | 1x |
| Sonnet 4.6 | $3.00 | $15.00 | ~3.75x |
Typical Claude Code session: ~80% structured tasks + ~20% reasoning.
1.0 * $3.75 = $3.75 units0.8 * $1 + 0.2 * $3.75 = $1.55 unitsReal usage (orallexa trading agent) saw ~10x reduction because many calls are pure JSON parsing where Haiku is indistinguishable from Sonnet.
pip install claude-tier-router
from anthropic import Anthropic
from tier_router import TierRouter
router = TierRouter(Anthropic())
# Structured -> Haiku
resp = router.fast(messages=[{"role": "user", "content": "Extract ticker as JSON: ..."}])
# Reasoning -> Sonnet
resp = router.deep(messages=[{"role": "user", "content": "Critique this strategy: ..."}])
# Inspect cost
print(router.cost_breakdown())
# {'fast_calls': 3, 'deep_calls': 1, 'fast_cost_usd': 0.002, ...}
FAST_MODEL / DEEP_MODEL from tier_router so model upgrades land in one place.FinPos-style position sizer for trading decisions. Takes an upstream Judge direction (long/short/no_op), a bankroll, a volatility regime, and Kelly parameters — returns a fund/skip verdict with a Kelly-cap-respecting, drawdown-adjusted position size. Never emits a direction. Ports from Orallexa's Python engine to a callable skill inside Claude Desktop / Cursor / OpenCode. Pairs with any upstream direction source: a fundamental analyst, an ML model, a discretionary trader, or Orallexa's own 5-voice debate.
Run an Advocate/Critic/Judge debate over any decision with real tradeoffs. Use when the user asks whether to merge a PR, pick an architecture, hire a candidate, ship a feature, or make any judgment where both sides have valid points and a single-model answer would be too confident.