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 4.5Kimi K3 (batch)
Claude Haiku 4.5

Anthropic

Kimi K3 (batch)

Moonshot AI

Pricing
Input $/1M$1.00$2.28
Output $/1M$5.00$11.40
Blended $/1M (3:1)$2.00$4.56
Cache read $/1M$0.10$0.228
Cache write $/1M$1.25—
Quality indices
Intelligence Index7.417.4
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,1101,334
Web apps—1,271
Full-stack—1,287
Mobile apps—1,252
Android native—1,254
UI components1,0881,337
Data viz1,1201,348
SVG1,0151,298
3D1,0461,359
Game dev1,0811,351
Agentic game dev—1,202
Godot game dev—1,198
HTML slides—1,153
Python→PPTX slides—1,222
Code categories1,1001,348
ASCII art1,1231,351
blender3d—1,122
codetovideo—1,281
pdf—1,271
spreadsheet—1,050
Specs
Context window200K1.05M
Max output tokens64K16K
Input modalitiestext, image, filetext, image, video
TokenizerClaudeOther