Portkey
AI gateway with routing, guardrails, and prompt management
Portkey is profiled here as a Prompt Management tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
Portkey is an AI gateway and LLM operations platform founded in 2023 by Rohit Agarwal and Ayush Garg. It sits between an application and hundreds of model providers, adding fallbacks, caching, guardrails, and cost tracking through one integration. The gateway core is open source, and the hosted platform layers prompt management and organization-wide observability on top of it. Gateway configs are versioned objects, so routing behavior changes ship without redeploying application code.
Key Capabilities:
Unified API across hundreds of models with automatic fallbacks and load balancing
Simple and semantic caching to cut latency and spend
Prompt versioning, templating, and a collaborative playground
Input and output guardrails with PII redaction
OpenTelemetry-based logs, traces, and cost analytics
Virtual keys with budgets and rate limits per team
Alternative tools
- Google AI Studio
Free browser workspace for prototyping with Gemini models
- Basalt
Collaborative prompt management and deployment for AI teams
- Promptmetheus
Prompt engineering IDE for composing and testing LLM prompts
- BAML
A domain-specific language for typed LLM functions
- Langtail
Collaborative prompt playground with testing and deployment
- Lunary
Open-source prompt management and observability for LLM apps