Your queries. Dramatically faster.
Serverless functions in 20 global regions connecting to a real PostgreSQL database, directly and through PgBeam. Each bar shows connect + p50 query latency. No synthetic data, no mocked endpoints.
PgBeam Regions
6Regions where PgBeam currently runs proxy nodes. Queries are pooled and cached at the edge for the lowest latency.
Washington, D.C.
Waiting to run…
Portland
Waiting to run…
Dublin
Waiting to run…
Mumbai
Waiting to run…
Singapore
Waiting to run…
Tokyo
Waiting to run…
Other Regions
14Regions without proxy nodes yet. Queries are routed to the nearest PgBeam region. We're actively expanding and these regions are on our roadmap.
Cleveland
Waiting to run…
Montréal
Waiting to run…
San Francisco
Waiting to run…
São Paulo
Waiting to run…
London
Waiting to run…
Paris
Waiting to run…
Frankfurt
Waiting to run…
Stockholm
Waiting to run…
Dubai
Waiting to run…
Sydney
Waiting to run…
Hong Kong
Waiting to run…
Osaka
Waiting to run…
Seoul
Waiting to run…
Cape Town
Waiting to run…
Methodology
How these numbers are generated. No synthetic data, no cherry-picked runs.
Setup
Each region runs as a serverless function deployed to that specific edge location. The function makes real PostgreSQL connections over TLS to a database in us-east-1.
Displayed value
Connect + median query latency (p50). This is what a serverless function experiences on every cold invocation: TLS handshake, authentication, then execute.
Sampling
5 queries per scenario, first discarded as warmup. p50 from 4 samples using nearest-rank. Results cached for 1 hour via ISR; the re-run button triggers fresh measurements.
Direct
Fresh TLS connection from the serverless function straight to the database. No proxy, no pooling, no caching. This is the baseline that you get without PgBeam.
PgBeam MISS
Same query routed through PgBeam with cache intentionally bypassed (the query runs inside a transaction). The query still executes on the database, but benefits from connection pooling holding warm upstream connections.
PgBeam HIT
Same query through PgBeam served from the edge cache. The result is returned without touching the database. This is the best case and what the “× faster” badge reflects.
Fairness notes
- • The proxy connection pool is warmed before the MISS test (a throwaway connection), matching production steady state where pools are always hot.
- • The “× faster” badge compares cache HIT total vs direct total. Hover it to see the pool-only (MISS) speedup.
- • Benchmark results are cached at the CDN for 1 hour and refreshed in the background with new measurements.