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 4.5Trinity Large Thinking
Claude Haiku 4.5

Anthropic

Trinity Large Thinking

Arcee Ai

Pricing
Input $/1M$1.00$0.25
Output $/1M$5.00$0.80
Blended $/1M (3:1)$2.00$0.387
Cache read $/1M$0.10$0.06
Cache write $/1M$1.25
Quality indices
Intelligence Index16.910.8
Coding Index43.925.8
Math Index
Agentic Index81
Speed & latency
Output speed (tok/s)
Time to first token
Time to first answer token
Design Arena (Elo)
Website1,1351,149
UI components1,1151,061
Data viz1,1391,113
SVG1,0491,040
3D1,1011,110
Game dev1,1201,102
Code categories1,1301,132
ASCII art1,1591,060
Specs
Context window200K262K
Max output tokens64K80K
Input modalitiestext, image, filetext
TokenizerClaudeOther