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 Pro 0423
Claude Opus 4.6

Anthropic

DeepSeek V4 Pro 0423

DeepSeek

Pricing
Input $/1M$5.00$0.90
Output $/1M$25.00$1.50
Blended $/1M (3:1)$10.00$1.05
Cache read $/1M$0.50$0.25
Cache write $/1M$6.25—
Quality indices
Intelligence Index—20.8
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,2791,223
Web apps1,1791,000
Full-stack1,193948
Mobile apps1,197—
Android native1,180—
UI components1,2721,209
Data viz1,2751,198
SVG1,2171,128
3D1,2481,227
Game dev1,2621,215
Agentic game dev1,144—
Godot game dev—1,059
Code categories1,2741,226
ASCII art1,2381,131
blender3d1,008—
codetovideo1,124—
pdf1,184—
spreadsheet986—
Specs
Context window1M1.05M
Max output tokens128K393K
Input modalitiestext, image, filetext
TokenizerClaudeDeepSeek