Feel the Speed
Same answer, two throughputs
Pick a sample completion, set each pane's speed on a log scale from 10 to 5000 tokens/sec, and press Play. Timing is simulated per token, client-side, with real elapsed clocks.
Latency Budget Calculator
How long does your agent chain really take?
Agent latency multiplies: steps times tokens per step divided by throughput, plus per-step overhead. Watch each step fill on the timeline below.
What It Unlocks
Speed tiers map to product patterns
Single streamed chat reply. Users watch text arrive; anything multi-step feels like waiting for a build.
Responsive copilots and inline rewrite. One tool call per turn stays conversational.
Instant multi-draft UI: generate five variants and let users pick. Speculative tool use — run likely branches in parallel and discard the losers.
Whole-app regeneration on every keystroke, real-time agent swarms, and generation-as-rendering where the model output is the interface itself.
Check Your Intuition