Compare Nova 2 Lite from Amazon and DeepSeek V4 Pro 0423 from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.


Nova 2 Lite and DeepSeek V4 Pro 0423 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Nova 2 Lite, from Amazon, has a 1,000,000-token context window and is priced at $0.30/M tokens input, $2.50/M tokens output on OpenRouter.
DeepSeek V4 Pro 0423, from DeepSeek, has a 1,048,576-token context window and is priced at $0.45/M tokens input, $3/M tokens output on OpenRouter.
| Attribute | Nova 2 Lite | DeepSeek V4 Pro 0423 |
|---|---|---|
| Input price | $0.30/M tokens | $0.45/M tokens |
| Output price | $2.50/M tokens | $3/M tokens |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Intelligence Index | 12.5 | 30.1 |
| Coding Index | Not available | 58.7 |
| Agentic Index | Not available | Not available |
| Latency (p50) | 0.76 s | 0.96 s |
| Throughput (p50) | 114.0 tok/s | 84.0 tok/s |
Benchmark data updated
Nova 2 Lite is cheaper than DeepSeek V4 Pro 0423 on OpenRouter: Nova 2 Lite costs $0.30/M tokens input and $2.50/M tokens output, while DeepSeek V4 Pro 0423 costs $0.45/M tokens input and $3/M tokens output.
DeepSeek V4 Pro 0423 has the longer context window at 1,048,576 tokens, compared with 1,000,000 tokens for Nova 2 Lite.
Nova 2 Lite is faster on OpenRouter, generating a median 114.0 tokens per second compared with 84.0 tokens per second for DeepSeek V4 Pro 0423.