AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Opus 4.6DeepSeek V4 Flash 0423
Claude Opus 4.6

Anthropic

DeepSeek V4 Flash 0423

DeepSeek

Pricing
Input $/1M$5.00$0.09
Output $/1M$25.00$0.18
Blended $/1M (3:1)$10.00$0.113
Cache read $/1M$0.50$0.018
Cache write $/1M$6.25—
Quality indices
Intelligence Index——
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,2791,196
Web apps1,179—
Full-stack1,193—
Mobile apps1,197—
Android native1,180—
UI components1,2721,152
Data viz1,2751,122
SVG1,2171,145
3D1,2481,163
Game dev1,2621,181
Agentic game dev1,144—
Code categories1,2741,191
ASCII art1,2381,092
blender3d1,008—
codetovideo1,124—
pdf1,184—
spreadsheet986—
Specs
Context window1M1.05M
Max output tokens128K393K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek