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 4.6Qwen3 235B A22B Thinking 2507
Claude Opus 4.6

Anthropic

Qwen3 235B A22B Thinking 2507

Alibaba (Qwen)

Pricing
Input $/1M$5.00$0.45
Output $/1M$25.00$3.50
Blended $/1M (3:1)$10.00$1.21
Cache read $/1M$0.50—
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)
Website1,2791,041
Web apps1,179—
Full-stack1,193—
Mobile apps1,197—
Android native1,180—
UI components1,272933
Data viz1,275950
SVG1,217—
3D1,248972
Game dev1,262941
Agentic game dev1,144—
Code categories1,2741,018
ASCII art1,238—
blender3d1,008—
codetovideo1,124—
pdf1,184—
spreadsheet986—
Specs
Context window1M128K
Max output tokens128K16K
Input modalitiestext, image, filetext
TokenizerClaudeQwen3