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 K3.1 Pro (batch)
Claude Haiku 4.5

Anthropic

Kimi K3.1 Pro (batch)

Moonshot AI

Pricing
Input $/1M$1.00$0.372
Output $/1M$5.00$5.58
Blended $/1M (3:1)$2.00$1.67
Cache read $/1M$0.10$0.10
Cache write $/1M$1.25—
Quality indices
Intelligence Index7.446.5
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,1101,316
Web apps—1,299
Full-stack—1,323
Mobile apps—1,267
Android native—1,160
UI components1,0881,384
Data viz1,1201,292
SVG1,0151,324
3D1,0461,437
Game dev1,0811,397
Python→PPTX slides—1,286
Code categories1,1001,345
ASCII art1,1231,296
codetovideo—1,245
pdf—1,225
spreadsheet—1,314
Specs
Context window200K1.05M
Max output tokens64K944K
Input modalitiestext, image, filetext, image, video
TokenizerClaudeOther