Compare Nano Banana 2 (Gemini 3.1 Flash Image) from Google and Nova 2 Lite from Amazon on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | Nano Banana 2 (Gemini 3.1 Flash Image) | Nova 2 Lite |
|---|---|---|
| Input price | Not applicable | $0.30/M tokens |
| Output price | Not applicable | $2.50/M tokens |
| Price | $0.50/M tokens input, $60/M tokens output | $0.30/M tokens input, $2.50/M tokens output |
| Context window | 131,072 tokens | 1,000,000 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | Not available | 23.0 |
| Agentic Index | Not available | Not available |
| Latency (p50) | 0.96 s | 0.87 s |
| Throughput (p50) | 38.0 tok/s | 80.0 tok/s |
| Provided by | Amazon | |
| Model page | Nano Banana 2 (Gemini 3.1 Flash Image) model details, providers and pricing | Nova 2 Lite model details, providers and pricing |
Benchmark data updated
Nova 2 Lite has the longer context window at 1,000,000 tokens, compared with 131,072 tokens for Nano Banana 2 (Gemini 3.1 Flash Image).
Nova 2 Lite is faster on OpenRouter, generating a median 80.0 tokens per second compared with 38.0 tokens per second for Nano Banana 2 (Gemini 3.1 Flash Image).