The context window is how much text a model can consider at once, and some models support 1 million tokens of it. The check for whether a model qualifies now reads a per-model value, native1mHere, instead of calling a separate helper.
Why
Eligibility for 1M context is now decided from each model's own details.
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtThe finding does not say whether this changes which models actually qualify.
