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 V4.1 Flash 1017 (batch)
Claude Opus 4.6

Anthropic

DeepSeek V4.1 Flash 1017 (batch)

DeepSeek

Pricing
Input $/1M$5.00$0.036
Output $/1M$25.00$0.15
Blended $/1M (3:1)$10.00$0.065
Cache read $/1M$0.50$0.0030
Cache write $/1M$6.25—
Quality indices
Intelligence Index—32.6
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,2791,290
Web apps1,179—
Full-stack1,193—
Mobile apps1,197—
Android native1,180—
UI components1,2721,279
Data viz1,2751,271
SVG1,2171,241
3D1,2481,338
Game dev1,2621,249
Agentic game dev1,144—
Code categories1,2741,283
ASCII art1,2381,219
blender3d1,008—
codetovideo1,124—
pdf1,184—
spreadsheet9861,261
Specs
Context window1M1.05M
Max output tokens128K944K
Input modalitiestext, image, filetext, image
TokenizerClaudeDeepSeek