@PostgreSQL has long powered core @OpenAI products like ChatGPT and the API. Over the past year, our production load grew 10× and keeps rising. Today we run a single primary with nearly 50 read replicas in production, delivering low double-digit millisecond p99 client-side latency and five-nines availability. In our latest OpenAI Engineering blog, we unpack the optimizations we made to to scale @Azure PostgreSQL to millions of queries per second for more than 800M ChatGPT users. Check out the full post here: openai.com/index/scaling-… Reduce load in Primary: We only have one primary so we minimize its load wherever possible. Read traffic is offloaded to read replicas, and shardable write-heavy workloads are moved to sharded databases like CosmosDB.