Cost Aware Llm Pipeline

This is a practical blueprint for keeping LLM API costs under control without tanking quality. It shows you how to route simple tasks to cheap models like Haiku and complex ones to Sonnet, track spend with immutable dataclasses, retry only transient errors, and cache long system prompts. The code examples are concrete and composable. Most useful if you're processing batches where costs add up fast or need hard budget limits before you burn through your API quota. The model selection thresholds are opinionated but tunable, which is the right approach.

skills.sh installs: 5.6K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill cost-aware-llm-pipeline --agent claude-code

Installs into .claude/skills of the current project.

Files

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)

SKILL.md on GitHub