AiCostCompare

Claude Sonnet 5 vs DeepSeek V4 Pro 0423

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and DeepSeek V4 Pro 0423 (DeepSeek). Green cells mark the better value in each row.

Prices updated Nov 16, 2026, 4:26 PM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

DeepSeek V4 Pro 0423

DeepSeek

Pricing
Input $/1M$2.00$0.90
Output $/1M$10.00$1.50
Blended $/1M (3:1)$4.00$1.05
RAG example (30K in / 2K out)$0.08$0.03
Quality & speed
Intelligence Index—20.8
Coding Index71.5—
Agentic Index43.6—
Output speed (tok/s)——
Time to first token——
Specs
Context window1M1.05M
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Sonnet 5 or DeepSeek V4 Pro 0423?

DeepSeek V4 Pro 0423 has the lower blended API price at $1.05 per 1M tokens (3:1 input:output mix), versus $4.00 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), DeepSeek V4 Pro 0423 costs about $0.03 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and DeepSeek V4 Pro 0423 offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

DeepSeek V4 Pro 0423 leads on the Artificial Analysis Intelligence Index (20.8 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.