Portkey
AI gateway for reliable and fast LLM applications
LLM APIs & InferenceFree + Pro plans★ 6,000Works with OpenClaw
About Portkey
Portkey is an AI gateway that makes LLM applications reliable and fast. It provides automatic fallbacks, load balancing, caching, rate limiting, and observability for production AI applications.
Features
AI gateway
Fallbacks
Load balancing
Caching
Observability
The tally
FOR
- +Automatic fallbacks
- +Load balancing
- +Request caching
- +Observability built-in
- +Open-source gateway
AGAINST
- −Added infrastructure layer
- −Learning curve
- −Some features need Pro
- −Latency overhead
Related concepts
Kept nearby
Vercel AI Gateway
Unified API gateway for routing app calls across hundreds of AI models
Free monthly credits; pay-as-you-go at provider list price with no markup
Hugging Face
The AI community platform with 500K+ models and datasets
Free + Pro $9/mo + Enterprise · ★ 140,000
Fireworks AI
Fast and efficient LLM inference platform
Pay-per-use
Together AI
Fast inference and fine-tuning for open-source models
Pay-per-use
Browse all LLM APIs & Inference tools →