What changed
Copilot cloud agent added automatic model selection based on system health and model performance, with a 10% multiplier discount and no weekly rate limit. Days later, GitHub added Claude Haiku 4.5 and GPT-5.4-mini at a 0.33-times multiplier for simpler tasks.
Why it matters
Mainstream developer tools are abandoning the idea that every task should use one flagship model; routing is now part of the product and billing model.
What to do
Route routine edits to smaller models, keep explicit escalation rules for complexity or failed validation and compare cost per merged change rather than token price.
Caveat
GitHub does not disclose the full routing policy or task-level quality data, so automatic selection is convenient but not independently auditable.