Command Palette

Search for a command to run...

Free the Models: Harness Design at the Frontier

Replit stopped routing work for the model and let the model decide. Here are the numbers.

Free the Models: Harness Design at the Frontier

About Free the Models: Harness Design at the Frontier

Replit argues that model routers have a built-in ceiling: the router is always less capable than the model it is choosing for. So Replit Agent now lets the frontier model decide how hard to think, when to hand work off, and which specialist subagent (code, UI design, slides, writing) takes each step.

Why it matters: on DeepSWE, Replit Agent scored 72% at $2.11 a task against 74% at $4.43 for Astra alone; on Terminal-Bench, 49% at $2.53 against 60% at $5.86. Models also use the same freedom differently: GPT-6 Astra reused briefed workers 42% of the time, while Fable models rarely used general workers.

Read it if you are building an agent and are about to hard-code which model or step handles what.

← Back to Resources