AI gateway and control plane for production GenAI: routes calls across 250+ LLMs with one unified API, plus guardrails, prompt management, observability, budgets, and an MCP-aware agent runtime.
AI gateway and control plane for production GenAI: routes calls across 250+ LLMs with one unified API, plus guardrails, prompt management, observability, budgets, and an MCP-aware agent runtime.
Portkey is an opinionated AI control plane that sits between your application and your LLM providers. The core is an AI gateway: a single endpoint that proxies to 250+ models from OpenAI, Anthropic, Google, Mistral, AWS Bedrock, Azure OpenAI, Cohere, Together, Groq, Fireworks, and others, with config-driven routing rules, fallbacks, load balancing, semantic caching, and retries. Around that gateway, Portkey layers a prompt library with versioned templates, an evals system for offline and online testing, guardrails (PII, jailbreak, toxicity, JSON schema, custom checks), and full request-level observability with cost and latency dashboards. For enterprises, Portkey adds RBAC, virtual keys, per-team budgets and rate limits, and SOC 2 / HIPAA / GDPR posture, plus self-hosted and BYOC deployments. The newer Agents product treats the gateway as the runtime for MCP-style tool-using agents: you register tools (including MCP servers), models, and policies once, then any agent in the org can call them through Portkey with central logging and budget enforcement.
Was this helpful?
Feature information is available on the official website.
View Features →$0
Paid plan with higher request limits, SSO, and team features
Custom
Ready to get started with Portkey?
View Pricing Options →Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
LLM Gateway
Unified API gateway to 400+ LLMs across every major and minor provider — one OpenAI-compatible endpoint, one bill, transparent per-model pricing, and automatic fallback when a provider goes down.
Deployment & Hosting
Cloudflare AI Gateway is a free AI observability and control layer that proxies requests to OpenAI, Anthropic, Google, and 25+ providers with caching, rate limiting, logging, DLP, and Guardrails.
LLM Observability
Open-source LLM observability, gateway, and cost analytics platform — proxy your OpenAI, Anthropic, or Bedrock calls through Helicone and get traces, caching, retries, rate limiting, and cost tracking in one line of code.
LLM Observability
Langfuse is an open-source LLM observability and engineering platform providing tracing, prompt management, evaluations, and dataset management for production AI applications.
LLM Evaluation
End-to-end evaluation, prompt playground, and observability platform for teams shipping LLM products — the tool most AI teams pick when spreadsheets stop scaling and vibes stop being enough.
No reviews yet. Be the first to share your experience!
Get started with Portkey and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →