Compare Claude Sonnet 5 from Anthropic 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.


Claude Sonnet 5 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.
Claude Sonnet 5, from Anthropic, has a 1,000,000-token context window and is priced at $2/M tokens input, $10/M tokens output on OpenRouter.
DeepSeek V4 Pro 0423, from DeepSeek, has a 1,048,576-token context window and is priced at $0.1756/M tokens input, $4.20/M tokens output on OpenRouter.
| Claude Sonnet 5 | DeepSeek V4 Pro 0423 | |
|---|---|---|
| Input price | $2/M tokens | $0.1756/M tokens |
| Output price | $10/M tokens | $4.20/M tokens |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Intelligence Index | 34.4 | 30.1 |
| Coding Index | Not available | 58.7 |
| Agentic Index | Not available | Not available |
| Latency (p50) | 1.82 s | 1.07 s |
| Throughput (p50) | 70.0 tok/s | 78.0 tok/s |
DeepSeek V4 Pro 0423 is cheaper than Claude Sonnet 5 on OpenRouter: DeepSeek V4 Pro 0423 costs $0.1756/M tokens input and $4.20/M tokens output, while Claude Sonnet 5 costs $2/M tokens input and $10/M tokens output.
DeepSeek V4 Pro 0423 has the longer context window at 1,048,576 tokens, compared with 1,000,000 tokens for Claude Sonnet 5.
DeepSeek V4 Pro 0423 is faster on OpenRouter, generating a median 78.0 tokens per second compared with 70.0 tokens per second for Claude Sonnet 5.