Portkey — AI Gateway for Production LLM Apps
You are an expert in Portkey, the AI gateway that sits between your app and LLM providers. You help developers add caching, fallbacks, load balancing, request retries, guardrails, semantic caching, budget limits, and observability to LLM calls — using a single unified API that works with 200+ models from OpenAI, Anthropic, Google, and open-source providers.
Best use case
Portkey — AI Gateway for Production LLM Apps is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
You are an expert in Portkey, the AI gateway that sits between your app and LLM providers. You help developers add caching, fallbacks, load balancing, request retries, guardrails, semantic caching, budget limits, and observability to LLM calls — using a single unified API that works with 200+ models from OpenAI, Anthropic, Google, and open-source providers.
Teams using Portkey — AI Gateway for Production LLM Apps should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/portkey/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Portkey — AI Gateway for Production LLM Apps Compares
| Feature / Agent | Portkey — AI Gateway for Production LLM Apps | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
You are an expert in Portkey, the AI gateway that sits between your app and LLM providers. You help developers add caching, fallbacks, load balancing, request retries, guardrails, semantic caching, budget limits, and observability to LLM calls — using a single unified API that works with 200+ models from OpenAI, Anthropic, Google, and open-source providers.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Portkey — AI Gateway for Production LLM Apps
You are an expert in Portkey, the AI gateway that sits between your app and LLM providers. You help developers add caching, fallbacks, load balancing, request retries, guardrails, semantic caching, budget limits, and observability to LLM calls — using a single unified API that works with 200+ models from OpenAI, Anthropic, Google, and open-source providers.
## Core Capabilities
```typescript
import Portkey from "portkey-ai";
const portkey = new Portkey({
apiKey: process.env.PORTKEY_API_KEY,
config: {
strategy: { mode: "fallback" }, // Auto-fallback on errors
targets: [
{
provider: "openai", api_key: process.env.OPENAI_KEY,
override_params: { model: "gpt-4o" },
weight: 0.7,
},
{
provider: "anthropic", api_key: process.env.ANTHROPIC_KEY,
override_params: { model: "claude-sonnet-4-20250514" },
weight: 0.3,
},
],
cache: { mode: "semantic", max_age: 3600 }, // Semantic caching
retry: { attempts: 3, on_status_codes: [429, 500, 503] },
},
});
// Use like OpenAI SDK — Portkey handles routing, caching, fallbacks
const response = await portkey.chat.completions.create({
messages: [{ role: "user", content: "Explain microservices" }],
max_tokens: 1024,
});
// Guardrails
const guarded = new Portkey({
apiKey: process.env.PORTKEY_API_KEY,
config: {
before_request_hooks: [{ type: "guardrail", id: "no-pii" }],
after_request_hooks: [{ type: "guardrail", id: "no-hallucination" }],
},
});
// Budget limits
// Set in Portkey dashboard: max $100/day per API key
```
## Installation
```bash
npm install portkey-ai
# or
pip install portkey-ai
```
## Best Practices
1. **OpenAI SDK compatible** — Drop-in replacement; change import and add config; existing code works
2. **Fallbacks** — Route to backup provider when primary fails; 99.99% effective uptime
3. **Semantic caching** — Cache similar (not just identical) queries; 40-60% cache hit rate typical
4. **Load balancing** — Split traffic across providers by weight; optimize cost vs quality
5. **Retry with backoff** — Auto-retry on 429/500/503; configurable attempts and status codes
6. **Guardrails** — PII detection, content moderation, hallucination checks; pre and post request
7. **Budget limits** — Set per-key spending caps; prevent runaway costs from bugs or abuse
8. **Observability** — Dashboard shows latency, cost, tokens, errors per provider; no additional SDKRelated Skills
genkit-production-expert
Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.
building-api-gateway
Create API gateways with routing, load balancing, rate limiting, and authentication. Use when routing and managing multiple API services. Trigger with phrases like "build API gateway", "create API router", or "setup API gateway".
api-gateway-config
Api Gateway Config - Auto-activating skill for AWS Skills. Triggers on: api gateway config, api gateway config Part of the AWS Skills skill category.
power-apps-code-app-scaffold
Scaffold a complete Power Apps Code App project with PAC CLI setup, SDK integration, and connector configuration
dataverse-python-production-code
Generate production-ready Python code using Dataverse SDK with error handling, optimization, and best practices
azure-static-web-apps
Helps create, configure, and deploy Azure Static Web Apps using the SWA CLI. Use when deploying static sites to Azure, setting up SWA local development, configuring staticwebapp.config.json, adding Azure Functions APIs to SWA, or setting up GitHub Actions CI/CD for Static Web Apps.
developing-ios-apps
Develops iOS/macOS applications with XcodeGen, SwiftUI, and SPM. Handles Apple Developer signing, notarization, and CI/CD pipelines. Triggers on XcodeGen project.yml, SPM dependency issues, device deployment, code signing errors (Error -25294, keychain mismatch, adhoc fallback, EMFILE, notarization credential conflict, continueOnError), camera/AVFoundation debugging, iOS version compatibility, "Library not loaded @rpath", Electron @electron/osx-sign/@electron/notarize config, notarytool, GitHub Actions secrets in conditionals, or certificate/provisioning problems. Use when building iOS/macOS apps, fixing Xcode build failures, deploying to real devices, or configuring CI/CD signing pipelines.
../../../marketing-skill/content-production/SKILL.md
No description provided.
deploying-to-production
Automate creating a GitHub repository and deploying a web project to Vercel. Use when the user asks to deploy a website/app to production, publish a project, or set up GitHub + Vercel deployment.
sleek-design-mobile-apps
Use when the user wants to design a mobile app, create screens, build UI, or interact with their Sleek projects. Covers high-level requests ("design an app that does X") and specific ones ("list my projects", "create a new project", "screenshot that screen").
shopify-apps
Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions. Use when: shopify app, shopify, embedded app, polaris, app bridge.
production-code-audit
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations