openrouter-caching-strategy

# OpenRouter Caching Strategy ## Overview OpenRouter charges per token, so caching identical or similar requests can dramatically cut costs. Deterministic requests (`temperature=0`) with the same model and messages produce identical outputs -- these are safe to cache. This skill covers in-memory caching, persistent caching with TTL, and Anthropic prompt caching via OpenRouter. ## In-Memory Cache ```python import os, hashlib, json, time from typing import Optional from openai import OpenAI client = OpenAI( base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"], default_headers={"HTTP-Referer": "https://my-app.com", "X-Title": "my-app"}, ) class LLMCache: def __init__(self, ttl_seconds: int = 3600): self._cache: dict[str, tuple[dict, float]] = {} self._ttl = ttl_seconds self.hits = 0 self.misses = 0 def _key(self, model: str, messages: list, **kwargs) -> str: blob = json.dumps({"model": model, "messages": messages, **kwargs}, sort_keys=True) return hashlib.sha256(blob.encode()).hexdigest() def get(self, model: str, messages: list, **kwargs) -> Optional[dict]: k = self._key(model, messages, **kwargs) if k in self._cache: data, ts = self._cache[k] if time.time() - ts < self._ttl: self.hits += 1 return data del self._cache[k] self.misses += 1 return None def set(self, mode...