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 Haiku 4.5Hy3
Claude Haiku 4.5

Anthropic

Hy3

Tencent

Pricing
Input $/1M$1.00$0.083
Output $/1M$5.00$0.33
Blended $/1M (3:1)$2.00$0.144
Cache read $/1M$0.10$0.021
Cache write $/1M$1.25—
Quality indices
Intelligence Index7.4—
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,1101,170
UI components1,0881,151
Data viz1,1201,120
SVG1,015—
3D1,0461,149
Game dev1,0811,119
Code categories1,1001,161
ASCII art1,123—
Specs
Context window200K262K
Max output tokens64K128K
Input modalitiestext, image, filetext
TokenizerClaudeOther