Cloudflare AI Gateway
LLM gateway with caching, analytics, and rate limiting
About
LLM gateway from Cloudflare that sits in front of any AI provider and adds request caching, cost analytics, rate limiting, and fallback routing. Zero-config for teams already on Cloudflare Workers. Free tier available on all Cloudflare plans.
Choose Cloudflare AI Gateway when…
- •You're already deploying on Cloudflare Workers or Pages
- •You want LLM caching and cost analytics with zero infrastructure overhead
- •You need a lightweight gateway without running LiteLLM yourself
Builder Slot
A gateway that normalizes calls across providers — one API for all models, with fallbacks
Other tools in this slot:
Stack Genome Detection
AIchitect's Genome scanner detects Cloudflare AI Gateway in your project via these signals:
CLOUDFLARE_API_TOKENIntegrates with (1)
Cloudflare AI Gateway proxies OpenAI traffic, adding caching, rate limits, fallbacks, and analytics without code changes — clients keep using the OpenAI SDK, just pointed at the gateway URL.
→ Add caching, fallbacks, and rate limits in front of OpenAI without touching application code.
Alternatives to consider (2)
Pricing
Badge
Add to your GitHub README
[](https://www.aichitect.dev/tool/cloudflare-ai-gateway)Explore the full AI landscape
See how Cloudflare AI Gateway fits into the bigger picture — browse all 207 tools and their relationships.