Project
Cloudflare service that routes, caches, logs, and manages API calls to AI models through a single gateway layer for developers and agents.
Cloudflare now sells web search from Ceramic.ai, Exa and Linkup through AI Gateway at partner list prices, billed from gateway credits with no markup. Teams already on the gateway skip a separate search vendor account, though their agents still have to issue each search call.
Reality
Cloudflare put its Monetization Gateway into closed beta, letting domain owners charge AI agents per request via HTTP 402, with four use cases in production. Cloudflare scopes it to APIs, tools and data, where each request is a single use.
Perspective Coverage
3 publishersReality
Cloudflare's Auto Router, now in public beta, picks a model per AI Gateway request and cut costs by up to 30% in the company's own OpenCode use. How much of that transfers depends on how much of a team's traffic never needed a frontier model.
Reality
LiteLLM works as a drop-in OpenAI replacement for teams running their own clusters, while managed gateways suit teams renting inference. OpenRouter's reported $113M round at a $1.3B valuation funds the rented side.
Reality
Fastly's AI Runtime Control is an endpoint you point an application at. It issues virtual keys against your own model provider account, and a key can carry a dollar budget, a rate limit and an ordered list of fallback models.
Reality
The early-access service reads live traffic to work out which findings matter, then produces a scoped firewall rule and a draft patch for review, so the mitigation is what actually ships while the code fix waits on engineers.
Reality
Centralising prompt checks and PII filters at the gateway mirrors putting TLS at the edge, and the arithmetic backs that comparison. The semantic checks themselves, though, work nothing like TLS termination.
Reality