cost-aware-llm-pipeline
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Use when LLM spend needs to come down, or when routing tasks across model tiers and budgets.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- cost-aware-llm-pipeline
- metadata
- { "origin": "ECC" }
- description
- Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Use when LLM spend needs to come down, or when routing tasks across model tiers and budgets.
03 SKILL.md 正文
Cost-Aware LLM Pipeline
Patterns for controlling LLM API costs while maintaining quality. Combines model routing, budget tracking, retry logic, and prompt caching into a composable pipeline.
When to Activate
- Building applications that call LLM APIs (Claude, GPT, etc.)
- Processing batches of items with varying complexity
- Need to stay within a budget for API spend
- Optimizing cost without sacrificing quality on complex tasks
Core Concepts
1. Model Routing by Task Complexity
Automatically select cheaper models for simple tasks, reserving expensive models for complex ones.
MODEL_SONNET = "claude-sonnet-5"
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)
2. Immutable Cost Tracking
Track cumulative spend with frozen dataclasses. Each API call returns a new tracker — never mutates state.
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
3. Narrow Retry Logic
Retry only on transient errors. Fail fast on authentication or bad request errors.
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
4. Prompt Caching
Cache long system prompts to avoid resending them on every request.
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": system_prompt,
"cache_control": {"type": "ephemeral"}, # Cache this
},
{
"type": "text",
"text": user_input, # Variable part
},
],
}
]
Composition
Combine all four techniques in a single pipeline function:
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
Pricing Reference (2026)
| Model | Input ($/1M tokens) | Output ($/1M tokens) | Relative Cost |
|---|---|---|---|
| Haiku 3.5 (legacy) | $0.80 | $4.00 | 0.8x |
| Haiku 4.5 | $1.00 | $5.00 | 1x |
| Sonnet 5 | $2.00 | $10.00 | 2x |
| Sonnet 4.6 | $3.00 | $15.00 | 3x |
| Opus 4.8 | $5.00 | $25.00 | 5x |
| Fable 5 / Mythos 5 | $10.00 | $50.00 | 10x |
| Opus 4.0 / 4.1 (legacy) | $15.00 | $75.00 | 15x |
Best Practices
- Start with the cheapest model and only route to expensive models when complexity thresholds are met
- Set explicit budget limits before processing batches — fail early rather than overspend
- Log model selection decisions so you can tune thresholds based on real data
- Use prompt caching for system prompts over 1024 tokens — saves both cost and latency
- Never retry on authentication or validation errors — only transient failures (network, rate limit, server error)
Anti-Patterns to Avoid
- Using the most expensive model for all requests regardless of complexity
- Retrying on all errors (wastes budget on permanent failures)
- Mutating cost tracking state (makes debugging and auditing difficult)
- Hardcoding model names throughout the codebase (use constants or config)
- Ignoring prompt caching for repetitive system prompts
When to Use
- Any application calling Claude, OpenAI, or similar LLM APIs
- Batch processing pipelines where cost adds up quickly
- Multi-model architectures that need intelligent routing
- Production systems that need budget guardrails
04 同仓库更多 Skills
system-lifecycle-designer
Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.
style-sampling
Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for "an episode of", "in the style of", "sample this style", 「用这个风格做一集」. One video to copy is reverse-any-video.
reverse-any-video
Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.
typescript-patterns
TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.
test-collaboration
Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit/integration/contract/E2E/smoke classification, bug-to-test regression protection, consumer/provider contract testing, test-necessity review, and pre-delivery evidence review.
story-lifecycle
Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira/Linear/Taiga but needs structured delivery tracking.