DeepSeek Pro Latest vs Claude Sonnet 5
Side-by-side API pricing and Artificial Analysis performance for DeepSeek Pro Latest (~deepseek) and Claude Sonnet 5 (Anthropic). Green cells mark the better value in each row.
Prices updated Sep 19, 2026, 9:09 PM UTC · refreshed hourly
| DeepSeek Pro Latest ~deepseek | Claude Sonnet 5 Anthropic | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.578 | $2.00 |
| Output $/1M | $1.73 | $10.00 |
| Blended $/1M (3:1) | $0.867 | $4.00 |
| RAG example (30K in / 2K out) | $0.0208 | $0.08 |
| Quality & speed | ||
| Intelligence Index | — | 38.2 |
| Coding Index | — | 71.5 |
| Agentic Index | — | 44.3 |
| Output speed (tok/s) | — | 86 |
| Time to first token | — | 120.21s |
| Specs | ||
| Context window | 1.05M | 1M |
| Input modalities | text | text, image, file |
FAQ
Which is cheaper, DeepSeek Pro Latest or Claude Sonnet 5?
DeepSeek Pro Latest has the lower blended API price at $0.867 per 1M tokens (3:1 input:output mix), versus $4.00 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), DeepSeek Pro Latest costs about $0.0208 per request versus $0.08. Also compare context windows: DeepSeek Pro Latest offers 1.05M and Claude Sonnet 5 offers 1M.
Which scores higher on Artificial Analysis benchmarks?
Claude Sonnet 5 leads on the Artificial Analysis Intelligence Index (38.2 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.