The million-token context window is here, priced flat. So why does your coding agent still grep?

As of this month, the flagship coding models ship a million-token context window by default, and at least one major vendor now prices it flat: no beta flag, no surcharge above 200k — a 900k request bills at the same per-token rate as a 9k one. Which raises a fair question. My repo is 700k tokens, so why is this thing still running grep like it's 2024?

Two reasons, and both are measurable.

First, the meter. An agent re-sends its whole history as input on every turn: system prompt, tools, conversation, and anything you pasted. A 700k-token repo at $5 per million input tokens costs about $3.50 per turn. Forty turns into a working session, the paste alone has billed around $140, before the model has written a line of code. Prompt caching cuts the re-read to a tenth of the price, but it just makes those tokens cheaper — they still fill the window.

Second, reading quality drops long before the window is full. The lost-in-the-middle effect still holds: models read the start and end of a long context better than the center. The NoLiMa benchmark (ICML 2025) removed literal word overlap between question and content and 10 of 12 models fell below half their short-context baseline by 32k tokens. One model advertising 2M tokens of context held its quality bar to about 2k. Newer models do better. The direction hasn't changed. Even the vendor's own docs now warn that "more context isn't automatically better" and give the failure mode a name, context rot. The company charging per token is telling you to send fewer tokens.

So the tools treat your repo as a filesystem to query: grep the symbol, open the three files that matter, read 20k instead of 700k. Pasting everything still has one real home — single-shot questions where breadth is the point and the conversation ends with the answer. For a forty-turn coding session, grep is simply the cheaper of the two readers, and the smarter one.