Model techniques map
Techniquesmodel architecturecontext capacity

implementation detail · filed under model architecture

256K context window

A context capacity of 256K tokens, distinct from the one-million-token window.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Step 3.7 Flash supports a 256k context window

coremodel architecturein Step 3.7 FlashStepFun

Filed alongside

Other methods under model architecture :: context capacity.