Customers

The teams shipping AI at scale run on Relay.

From seed-stage startups to public companies, thousands of engineering teams route, monitor, and govern every LLM request through Relay.

Trusted by teams at
Notion
Ramp
Vercel
Linear
Perplexity
Anthropic
Mistral
Hugging Face
Replit
Cursor
Retool
Stripe
Shopify
Datadog
Airtable
Figma
Loom
Intercom

Customer stories

Ramp
63%
lower inference cost

"Relay cut our LLM spend by nearly two-thirds in the first quarter. The dynamic routing across providers paid for itself in a week."

Priya Natarajan
Staff Engineer, Platform
Linear
12ms
p50 added latency

"We were skeptical about adding a gateway in the hot path. After a month of load testing, Relay added less latency than our own load balancer."

Marcus Hale
Principal Engineer
Perplexity
4.2B
requests / month

"Relay is the only gateway that didn't fall over at our scale. Observability is genuinely the best we've used — every request is one click away."

Anya Kowalski
Director of Infrastructure
12B+
Monthly requests routed
38%
Average cost reduction
99.99%
Gateway uptime, trailing 90 days
2,400+
Teams in production