Amazon Nova Lite 1.0 vs Qwen3 Coder 30B A3B Instruct
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Nova Lite 1.0 is 1.2× cheaper at a typical mix of 3 input tokens per output token.
- Both accept prompts up to 262K tokens.
- Qwen3 Coder 30B A3B Instruct is the newer model (released 2025-07-31).
| Nova Lite 1.0 | Qwen3 Coder 30B A3B Instruct | |
|---|---|---|
| Vendor | Amazon | Qwen |
| Released | 2024-12-05 | 2025-07-31 |
| Input / 1M | $0.06 | $0.07 |
| Output / 1M | $0.24 | $0.28 |
| Cached input / 1M | — | — |
| Blended / 1M (3:1) | $0.105 | $0.123 |
| Context | 300K | 262K |
| Max output | 5K | 236K |
| Accepts | text, image | text |
| Reasoning | No | No |
| Providers on OpenRouter | 2 | 2 |
| Cheapest provider, output | $0.24 | $0.28 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | Operational |
Cost calculator
Nova Lite 1.0
$7.20 per month$0.24 per day
Qwen3 Coder 30B A3B Instruct
$8.40 per month$0.28 per day
Nova Lite 1.0 saves $1.20 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Nova Lite 1.0 with
Compare Qwen3 Coder 30B A3B Instruct with