The small, fast Google model is Nano Banana (Gemini 2.5 Flash Image) — the efficient tier at 224 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. Gemini 2.5 Flash Lite Preview 09-2025 (217 t/s) and Gemini 3.5 Flash (156 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 Google model is Nano Banana (Gemini 2.5 Flash Image) — the efficient tier at 224 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. Gemini 2.5 Flash Lite Preview 09-2025 (217 t/s) and Gemini 3.5 Flash (156 t/s) round out the top three.
Gemini 2.5 Flash Lite Preview 09-2025 (217 t/s) is the closest alternative on this metric, followed by Gemini 3.5 Flash (156 t/s). See the full ranking above for the tradeoffs.
modelgrep tracks 26 Google models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Gemini 3 Flash Preview. 17 of them qualify for this ranking.