The small, fast Amazon model is Nova 2 Lite — the efficient tier at 119 tokens/sec and $0.300 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Nova Micro 1.0 (97 t/s) and Nova Lite 1.0 (76 t/s) round out the top three.
Compact, efficient models — the small/mini/flash/haiku tier — ranked by output speed. These trade a little raw intelligence for low cost and high throughput, which is the right tradeoff for chat, classification, extraction and other high-volume work.
The small, fast Amazon model is Nova 2 Lite — the efficient tier at 119 tokens/sec and $0.300 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Nova Micro 1.0 (97 t/s) and Nova Lite 1.0 (76 t/s) round out the top three.
Nova Micro 1.0 (97 t/s) is the closest alternative on this metric, followed by Nova Lite 1.0 (76 t/s). See the full ranking above for the tradeoffs.
modelgrep tracks 5 Amazon models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Nova 2 Lite. 3 of them qualify for this ranking.