Openrouter Caching Strategy

What it does

When your agent uses it

• Optimizing repeat queries
• Building RAG systems
• Reducing API spend

Example prompts

• “openrouter cache”
• “cache llm responses”
• “openrouter caching”
• “/openrouter-caching-strategy”

Requirements

• Python 3
• Node.js
• A credential in OPENROUTER_API_KEY
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Bash(python3:*), Bash(node:*)

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm the requests you want to cache are deterministic (temperature=0); non-zero temperatures produce different outputs each call and…
2. 2Start with the In-Memory Cache: LLMCache plus cached_completion() gives you TTL expiry and hit/miss counters in a single process.
3. 3For multi-instance deployments, switch to Persistent Cache with Redis — redis_cached_completion() stores results under or: keys with…
4. 4Build keys per Cache Key Design: include the model ID (with variants like :floor), messages, temperature, max_tokens, and top_p; exclude…
5. 5For large static system prompts (RAG context), add cache_control: {"type": "ephemeral"} per Anthropic Prompt Caching via OpenRouter…
6. 6Wire the Cache Invalidation table: flush per-model keys on model version updates, flush everything on system prompt changes, and let TTL…

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Grep
  • Bash(python3:*)
  • Bash(node:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • openrouter.ai

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENROUTER_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Openrouter Caching Strategy loads about 2.4k tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 580 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~71

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 580 words, ~2,385 tokens.

name

openrouter-caching-strategy

description

Implement caching for OpenRouter API responses to reduce cost and latency. Use when optimizing repeat queries, building RAG systems, or reducing API spend. Triggers: 'openrouter cache', 'cache llm responses', 'openrouter caching', 'reduce openrouter cost'.

allowed-tools

Read, Write, Edit, Grep, Bash(python3:*), Bash(node:*)

compatibility

Designed for Claude Code

version

1.20.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, openrouter, caching, cost-optimization

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, model: str, messages: list, response: dict, **kwargs):
        k = self._key(model, messages, **kwargs)
        self._cache[k] = (response, time.time())

cache = LLMCache(ttl_seconds=1800)

def cached_completion(messages, model="anthropic/claude-3.5-sonnet", **kwargs):
    """Only cache deterministic requests (temperature=0)."""
    kwargs.setdefault("temperature", 0)
    kwargs.setdefault("max_tokens", 1024)

    cached = cache.get(model, messages, **kwargs)
    if cached:
        return cached

    response = client.chat.completions.create(model=model, messages=messages, **kwargs)
    result = {
        "content": response.choices[0].message.content,
        "model": response.model,
        "usage": {"prompt": response.usage.prompt_tokens, "completion": response.usage.completion_tokens},
    }
    cache.set(model, messages, result, **kwargs)
    return result

import redis, json, hashlib

r = redis.Redis(host="localhost", port=6379, db=0)

def redis_cached_completion(messages, model="openai/gpt-4o-mini", ttl=3600, **kwargs):
    """Cache in Redis with automatic TTL expiry."""
    kwargs["temperature"] = 0  # Must be deterministic
    key = f"or:{hashlib.sha256(json.dumps({'m': model, 'msgs': messages, **kwargs}, sort_keys=True).encode()).hexdigest()}"

    cached = r.get(key)
    if cached:
        return json.loads(cached)

    response = client.chat.completions.create(model=model, messages=messages, **kwargs)
    result = {
        "content": response.choices[0].message.content,
        "model": response.model,
        "tokens": response.usage.prompt_tokens + response.usage.completion_tokens,
    }
    r.setex(key, ttl, json.dumps(result))
    return result

# Mark large static content blocks with cache_control
response = client.chat.completions.create(
    model="anthropic/claude-3.5-sonnet",
    messages=[
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": "You are an expert. Here is the full source:\n" + large_context,
                    "cache_control": {"type": "ephemeral"},  # Cache this block
                }
            ],
        },
        {"role": "user", "content": "What does the main() function do?"},
    ],
    max_tokens=1024,
)
# First call: cache_creation_input_tokens charged at 1.25x
# Subsequent: cache_read_input_tokens charged at 0.1x (90% savings)

def cache_key(model: str, messages: list, **params) -> str:
    """Deterministic cache key. Include everything that affects output.

    Include: model ID (with variant like :floor), messages, temperature,
    max_tokens, top_p, transforms, provider routing.
    Exclude: stream (doesn't affect content), HTTP-Referer, X-Title.
    """
    canonical = json.dumps({
        "model": model, "messages": messages,
        "temperature": params.get("temperature", 0),
        "max_tokens": params.get("max_tokens"),
        "top_p": params.get("top_p"),
    }, sort_keys=True)
    return hashlib.sha256(canonical.encode()).hexdigest()

result1 = cached_completion("What is Python?")   # [Cache MISS] key=3f8a92c1... (stored)
result2 = cached_completion("What is Python?")   # [Cache HIT] key=3f8a92c1...
print(f"Hit rate: {cache.hit_rate:.0%}")         # Hit rate: 50%

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in skills/.curated/openrouter-caching-strategy of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/cache-invalidation.md
• references/caching-strategies.md
• references/cost-savings-analysis.md
• references/errors.md
• references/examples.md
• references/in-memory-caching.md
• references/redis-caching.md
• references/semantic-caching.md

Open the folder on GitHubat commit cfae287