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.

Pareto LatestClaude Haiku 4.5
Pareto Latest

~unbiased

Claude Haiku 4.5

Anthropic

Pricing
Input $/1M$0.80$1.00
Output $/1M$3.20$5.00
Blended $/1M (3:1)$1.40$2.00
Cache read $/1M$0.03$0.10
Cache write $/1M—$1.25
Quality indices
Intelligence Index—7.4
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website—1,110
UI components—1,088
Data viz—1,120
SVG—1,015
3D—1,046
Game dev—1,081
Code categories—1,100
ASCII art—1,123
Specs
Context window1.05M200K
Max output tokens131K64K
Input modalitiestext, imagetext, image, file
TokenizerRouterClaude