Compare Nova 2 Lite from Amazon and DeepSeek V3.1 Terminus 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 V3.1 Terminus 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 V3.1 Terminus, from DeepSeek, has a 163,840-token context window and is priced at $0.27/M tokens input, $1/M tokens output on OpenRouter.
| Attribute | Nova 2 Lite | DeepSeek V3.1 Terminus |
|---|---|---|
| Input price | $0.30/M tokens | $0.27/M tokens |
| Output price | $2.50/M tokens | $1/M tokens |
| Context window | 1,000,000 tokens | 163,840 tokens |
| Intelligence Index | 12.5 | 13.9 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 0.61 s | 1.81 s |
| Throughput (p50) | 182.0 tok/s | 19.0 tok/s |
Benchmark data updated
DeepSeek V3.1 Terminus is cheaper than Nova 2 Lite on OpenRouter: DeepSeek V3.1 Terminus costs $0.27/M tokens input and $1/M tokens output, while Nova 2 Lite costs $0.30/M tokens input and $2.50/M tokens output.
Nova 2 Lite has the longer context window at 1,000,000 tokens, compared with 163,840 tokens for DeepSeek V3.1 Terminus.
Nova 2 Lite is faster on OpenRouter, generating a median 182.0 tokens per second compared with 19.0 tokens per second for DeepSeek V3.1 Terminus.