Small & Fast Google Models
The small, fast Google model is Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) — the efficient tier at 381 tokens/sec and $0.250 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 3.1 Flash Lite Preview (337 t/s) and Nano Banana (Gemini 2.5 Flash Image) (183 t/s) round out the top three.
- 1
gemini-3.1-flash-lite-imageReasoningJSONVision+1$0.250/M · 2.3s ttft · 66K ctx381 t/sSpeed - 2gemini-3.1-flash-lite-previewReasoningToolsJSON+225.0 intel · $0.250/M · 4.9s ttft337 t/sSpeed
- 3gemini-2.5-flash-imageJSONVisionImage out$0.300/M · 362ms ttft · 33K ctx183 t/sSpeed
- 4gemini-3.5-flash-liteReasoningToolsJSON+236.5 intel · $0.300/M · 575ms ttft137 t/sSpeed
- 5gemini-3.1-flash-imageReasoningJSONVision+1$0.500/M · 3.9s ttft · 131K ctx136 t/sSpeed
- 6gemini-3.1-flash-liteReasoningToolsJSON+225.0 intel · $0.250/M · 577ms ttft103 t/sSpeed
- 7gemini-3-pro-imageReasoningToolsJSON+2$2.00/M · 232ms ttft · 131K ctx51 t/sSpeed
- 8gemini-3-pro-image-previewReasoningJSONVision+1$2.00/M · 8.1s ttft · 66K ctx10 t/sSpeed
How this is ranked
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.
Frequently asked
What is the smallest, fastest Google model?
The small, fast Google model is Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) — the efficient tier at 381 tokens/sec and $0.250 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 3.1 Flash Lite Preview (337 t/s) and Nano Banana (Gemini 2.5 Flash Image) (183 t/s) round out the top three.
What's a good alternative to Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)?
Gemini 3.1 Flash Lite Preview (337 t/s) is the closest alternative on this metric, followed by Nano Banana (Gemini 2.5 Flash Image) (183 t/s). See the full ranking above for the tradeoffs.
How many Google models are there?
modelgrep tracks 30 Google models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Gemini 3.5 Flash. 8 of them qualify for this ranking.