Skip to main content

Simulation run on this device. Scenario values are not sent anywhere — the engine is fully local.

ai studio · free

Tokenizer Context Playground

Split text into tokens and watch word pieces, whitespace, and unicode add up.

Why does this 'short' prompt cost 4x the tokens?

Engine 1.0.0 · studio
100200000
4
2048200000
020000
Est. tokens
3500
Context fill
2.73%
Headroom tok
124500
Fits?
yes

Comfortable context headroom.

8000 chars ≈ 3500 tok

Method

  • Deterministic local model of the mechanism — knobs recompute outputs instantly with no network.
  • Numbers are teaching approximations, not production capacity guarantees.