There is noticeable trend across all agentic coding platforms that this situation is no longer sustainable.

With this kind of pricing (sonnet 4.6 has 9x multiplier, previously 1x) it begs the question why use Copilot to begin with.

You could easily just buy the tokens directly and have a lot more choice as well.

One reason I used it was that I wasn't locked into a single provider and switching them was as easy as changing a drop-down. Small feature? Sonnet or GPT5.4/mini? Large changes? Opus. And why not see how good Raptor Mini does this one refactor?

It also helped build an intuition of what wach model could do and which parts it was weaker at because you could try them almost side by side, especially if one model's output wasn't great.

That said, these were all side projects so nothing truly consequential. Otoh, you might leave some extra perf on the table but I found the models worked quite with the Copilot harness.

The problem is I can't afford the tokens! Even on my $10/mo plan, running either 100 opus, or 300 sonnet agent runs would cost hundreds of dollars - well above my budget!

Doesn't GitHub get volume discounting they can pass on to their Copilot customers?