Best fit
- LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。
affaan-m/ECC
LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/cost-aware-llm-pipeline"Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
According to the pinned SKILL.md from affaan-m/ECC: 在保持质量的同时控制 LLM API 成本的模式。将模型路由、预算跟踪、重试逻辑和提示词缓存组合成一个可组合的流水线。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/cost-aware-llm-pipeline"Best fit
Bring this context
Expected outputs
Key source sections
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
构建调用 LLM API(Claude、GPT 等)的应用程序时 处理具有不同复杂度的批量项目时 需要将 API 支出控制在预算范围内时 需要在复杂任务上优化成本而不牺牲质量时
自动为简单任务选择更便宜的模型,为复杂任务保留昂贵的模型。
自动为简单任务选择更便宜的模型,为复杂任务保留昂贵的模型。
使用冻结的数据类跟踪累计支出。每个 API 调用都会返回一个新的跟踪器 —— 永不改变状态。
仅在暂时性错误时重试。对于认证或错误请求错误,快速失败。
SkillSignal prompt templates
These prompts were written by SkillSignal from the source structure; they are not upstream text.
Task-start prompt
Confirm source fit, inputs, and outputs before acting.
Use cost-aware-llm-pipeline to help me with: [specific task]. Context: [files, data, or background]. Constraints: [environment, scope, and prohibited actions]. Before acting, check the pinned SKILL.md and explain which sections apply, what inputs are still missing, and what you will deliver.
Source-guided execution
Make the Agent explicitly follow the key extracted sections.
Apply the pinned cost-aware-llm-pipeline source to [task]. Pay particular attention to these source sections: “何时激活”, “核心概念”, “1. 根据任务复杂度进行模型路由”, “2. 不可变的成本跟踪”, “3. 窄范围重试逻辑”. Preserve the important decision at each step. Mark facts not covered by the source as “needs confirmation” instead of inventing them. Then verify the result against my acceptance criteria: [criteria].
Result-review prompt
Check omissions, permissions, and source drift before delivery.
Review the current cost-aware-llm-pipeline result: (1) does it satisfy the original task; (2) were any applicable steps or limits in the pinned SKILL.md missed; (3) did it perform any unauthorized file, command, network, or data action; and (4) which conclusions remain unverified? List issues first, then fix only what the source or user authorization supports.
Output checklist
The task matches the purpose documented in the SKILL.md.
The source section “何时激活” has been checked.
The source section “核心概念” has been checked.
The source section “1. 根据任务复杂度进行模型路由” has been checked.
The source section “2. 不可变的成本跟踪” has been checked.
Inputs, constraints, and acceptance criteria are explicit.
Unverified facts, compatibility, and outcome claims are clearly marked.
Any file, command, network, or data action has been reviewed.
Choose a different workflow
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailLLM APIの使用量のコスト最適化パターン — タスクの複雑さによるモデルルーティング、予算追跡、リトライロジック、プロンプトキャッシング。
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
A separate implementation from coreyhaines31/marketingskills; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
在保持质量的同时控制 LLM API 成本的模式。将模型路由、预算跟踪、重试逻辑和提示词缓存组合成一个可组合的流水线。
The catalog detected this source-specific install command: npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/cost-aware-llm-pipeline". Inspect the command and pinned source before running it.
No dedicated Agent platform is declared in the pinned source record.
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Compare before choosing
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
LLM APIの使用量のコスト最適化パターン — タスクの複雑さによるモデルルーティング、予算追跡、リトライロジック、プロンプトキャッシング。
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.
Use BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for the ui directive set.
在保持质量的同时控制 LLM API 成本的模式。将模型路由、预算跟踪、重试逻辑和提示词缓存组合成一个可组合的流水线。
自动为简单任务选择更便宜的模型,为复杂任务保留昂贵的模型。
MODEL_SONNET = "claude-sonnet-4-6"
MODEL_HAIKU = "claude-haiku-4-5-20251001"
_SONNET_TEXT_THRESHOLD = 10_000 # chars
_SONNET_ITEM_THRESHOLD = 30 # items
def select_model(
text_length: int,
item_count: int,
force_model: str | None = None,
) -> str:
"""Select model based on task complexity."""
if force_model is not None:
return force_model
if text_length >= _SONNET_TEXT_THRESHOLD or item_count >= _SONNET_ITEM_THRESHOLD:
return MODEL_SONNET # Complex task
return MODEL_HAIKU # Simple task (3-4x cheaper)
使用冻结的数据类跟踪累计支出。每个 API 调用都会返回一个新的跟踪器 —— 永不改变状态。
from dataclasses import dataclass
@dataclass(frozen=True, slots=True)
class CostRecord:
model: str
input_tokens: int
output_tokens: int
cost_usd: float
@dataclass(frozen=True, slots=True)
class CostTracker:
budget_limit: float = 1.00
records: tuple[CostRecord, ...] = ()
def add(self, record: CostRecord) -> "CostTracker":
"""Return new tracker with added record (never mutates self)."""
return CostTracker(
budget_limit=self.budget_limit,
records=(*self.records, record),
)
@property
def total_cost(self) -> float:
return sum(r.cost_usd for r in self.records)
@property
def over_budget(self) -> bool:
return self.total_cost > self.budget_limit
仅在暂时性错误时重试。对于认证或错误请求错误,快速失败。
from anthropic import (
APIConnectionError,
InternalServerError,
RateLimitError,
)
_RETRYABLE_ERRORS = (APIConnectionError, RateLimitError, InternalServerError)
_MAX_RETRIES = 3
def call_with_retry(func, *, max_retries: int = _MAX_RETRIES):
"""Retry only on transient errors, fail fast on others."""
for attempt in range(max_retries):
try:
return func()
except _RETRYABLE_ERRORS:
if attempt == max_retries - 1:
raise
time.sleep(2 ** attempt) # Exponential backoff
# AuthenticationError, BadRequestError etc. → raise immediately
缓存长的系统提示词,以避免在每个请求上重新发送它们。
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": system_prompt,
"cache_control": {"type": "ephemeral"}, # Cache this
},
{
"type": "text",
"text": user_input, # Variable part
},
],
}
]
将所有四种技术组合到一个流水线函数中:
def process(text: str, config: Config, tracker: CostTracker) -> tuple[Result, CostTracker]:
# 1. Route model
model = select_model(len(text), estimated_items, config.force_model)
# 2. Check budget
if tracker.over_budget:
raise BudgetExceededError(tracker.total_cost, tracker.budget_limit)
# 3. Call with retry + caching
response = call_with_retry(lambda: client.messages.create(
model=model,
messages=build_cached_messages(system_prompt, text),
))
# 4. Track cost (immutable)
record = CostRecord(model=model, input_tokens=..., output_tokens=..., cost_usd=...)
tracker = tracker.add(record)
return parse_result(response), tracker
| 模型 | 输入(美元/百万令牌) | 输出(美元/百万令牌) | 相对成本 |
|---|---|---|---|
| Haiku 4.5 | $0.80 | $4.00 | 1x |
| Sonnet 4.6 | $3.00 | $15.00 | ~4x |
| Opus 4.5 | $15.00 | $75.00 | ~19x |