Compare Claude Sonnet 4.5 from Anthropic and DeepSeek V3.1 Base 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.


Claude Sonnet 4.5 and DeepSeek V3.1 Base are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Claude Sonnet 4.5, from Anthropic, has a 1,000,000-token context window and is priced at $3/M tokens input, $15/M tokens output on OpenRouter.
DeepSeek V3.1 Base, from DeepSeek, has a 163,840-token context window and is priced by the provider serving it on OpenRouter.
| Claude Sonnet 4.5 | DeepSeek V3.1 Base | |
|---|---|---|
| Input price | $3/M tokens | Pricing varies by provider |
| Output price | $15/M tokens | Pricing varies by provider |
| Context window | 1,000,000 tokens | 163,840 tokens |
| Intelligence Index | 19.3 | Not available |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 1.42 s | Not available |
| Throughput (p50) | 37.0 tok/s | Not available |
Claude Sonnet 4.5 has the longer context window at 1,000,000 tokens, compared with 163,840 tokens for DeepSeek V3.1 Base.