DeepSeek V4 Flash Latest vs Claude Sonnet 5
Side-by-side API pricing and Artificial Analysis performance for DeepSeek V4 Flash Latest (~deepseek) and Claude Sonnet 5 (Anthropic). Green cells mark the better value in each row.
Prices updated Sep 15, 2026, 5:44 PM UTC · refreshed hourly
| DeepSeek V4 Flash Latest ~deepseek | Claude Sonnet 5 Anthropic | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.04 | $2.00 |
| Output $/1M | $0.10 | $10.00 |
| Blended $/1M (3:1) | $0.055 | $4.00 |
| RAG example (30K in / 2K out) | $0.0014 | $0.08 |
| Quality & speed | ||
| Intelligence Index | — | 38.4 |
| Coding Index | — | 71.5 |
| Agentic Index | — | 44.3 |
| Output speed (tok/s) | — | 84 |
| Time to first token | — | 125.08s |
| Specs | ||
| Context window | 1.31M | 1M |
| Input modalities | text | text, image, file |
FAQ
Which is cheaper, DeepSeek V4 Flash Latest or Claude Sonnet 5?
DeepSeek V4 Flash Latest has the lower blended API price at $0.055 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 V4 Flash Latest costs about $0.0014 per request versus $0.08. Also compare context windows: DeepSeek V4 Flash Latest offers 1.31M and Claude Sonnet 5 offers 1M.
Which scores higher on Artificial Analysis benchmarks?
Claude Sonnet 5 leads on the Artificial Analysis Intelligence Index (38.4 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.