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 4.6Grok 4.5
Claude Opus 4.6

Anthropic

Grok 4.5

xAI

Pricing
Input $/1M$5.00$2.00
Output $/1M$25.00$6.00
Blended $/1M (3:1)$10.00$3.00
Cache read $/1M$0.50$0.30
Cache write $/1M$6.25
Quality indices
Intelligence Index37.853.8
Coding Index72.4
Math Index
Agentic Index45.7
Speed & latency
Output speed (tok/s)5473
Time to first token1.89s9.69s
Time to first answer token1.89s9.69s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%93.1%
Humanity's Last Exam18.6%40.3%
SciCode45.7%54.1%
IFBench44.6%
AA-LCR (Long Context Reasoning)58.3%67.7%
Terminal-Bench Hard48.5%
Terminal-Bench 2.181.6%
τ²-Bench (Telecom)84.8%
τ³-Bench Banking32.6%
Design Arena (Elo)
Website1,3231,323
Web apps1,2611,270
Full-stack1,2791,302
Mobile apps1,280
Android native1,1951,263
UI components1,3361,331
Data viz1,3221,302
SVG1,274
3D1,3351,329
Game dev1,3371,330
Agentic game dev1,227
Godot game dev1,297
HTML slides1,240
Python→PPTX slides1,230
Code categories1,3271,323
ASCII art1,298
Specs
Context window1M500K
Max output tokens128K
Input modalitiestext, image, filetext, image, file
TokenizerClaudeGrok