NewCost and speed
How Mercor ships internal apps and billions of production tokens on one platform
Our short summary of Vercel’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on vercel.com (opens in a new tab)Problem
Batch jobs were stuck for up to 12 hours because model rate limits caused retries.
Solution
They added Vercel AI Gateway to route requests across providers, adding capacity and failover, reducing batch time to 2‑3 hours.
Batch jobs finish in 2‑3 hours
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on vercel.com (opens in a new tab)
CRED