Head-to-Head Pricing Benchmark
Side-by-side pricing and context window comparison for production model selection.
Default Recommendation (120M input + 60M output)
Google: Gemma 3n 4B is lower-cost for the default monthly workload scenario.
Adjust the workload in the calculator below to see a live recommendation for your usage.
| Metric | Amazon: Nova Lite 1.0 | Google: Gemma 3n 4B |
|---|---|---|
| Developer | amazon | |
| Context Window | 300,000 | 32,768 |
| Max Output Tokens | 5,120 | — |
| Input Cost / 1M Tokens | $0.0600 | $0.0600 |
| Output Cost / 1M Tokens | $0.2400 | $0.1200 |
| Projected Monthly Cost | $22 | $14 |
| Vision | ✅ Yes | ❌ No |
| Tool Calling | ✅ Yes | ❌ No |
| Structured Output | ❌ No | ❌ No |
| Reasoning | ❌ No | ❌ No |
| Web Search | ❌ No | ❌ No |
| Tokenizer | Nova | Other |
| MMLU Score | N/A | 48.8 |
| GPQA | N/A | 29.6 |
Price History
Current Input / 1M
$0.0600
Current Output / 1M
$0.2400
Price History
Current Input / 1M
$0.0600
Current Output / 1M
$0.1200
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
Adjust your workload to see projected monthly costs.
Amazon: Nova Lite 1.0
$22
per month
Google: Gemma 3n 4B
$14
per month
Lower costLive Recommendation
Google: Gemma 3n 4B is lower-cost at 120M input + 60M output tokens/month.
Continue evaluation with more “A vs B pricing” decision pages.