GitHub has released Project HydraFusion, a research preview that stops treating model choice as a one-time setting. Instead of routing your prompt to a single model, HydraFusion builds an execution plan per request. It can draft with one model, have a second model critique the draft, or escalate to a stronger model when a quality gate rejects the first attempt. Models come from multiple providers. The developer picks HydraFusion once, the same way they would pick any other model.
Is it deployable? Yes, but narrowly. HydraFusion is live as a research preview for users on all GitHub Copilot plans, inside GitHub Copilot CLI only. There are no open weights and no self-hosted path. Run /update, then /experimental on, then /model and select HydraFusion (Research Preview). Billing is per token consumed by whichever models the workflow invokes, at each model’s standard rate.
What the system actually does
HydraFusion follows Auto model selection, which GitHub shipped earlier in 2026 to match a task to one best-suited model. HydraFusion goes a step further and treats workflow selection as an optimization problem.
It reads capability signals for reasoning, code generation, debugging, and tool use. It then picks the least complex workflow expected to clear the quality bar, spending extra model calls only where they are likely to help.
