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 4.5MiniMax M3 (batch)
Claude Haiku 4.5

Anthropic

MiniMax M3 (batch)

MiniMax

Pricing
Input $/1M$1.00$0.224
Output $/1M$5.00$0.88
Blended $/1M (3:1)$2.00$0.388
Cache read $/1M$0.10$0.045
Cache write $/1M$1.25—
Quality indices
Intelligence Index7.418.9
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,1101,245
Web apps—1,183
Full-stack—1,174
Mobile apps—1,169
Android native—1,155
UI components1,0881,233
Data viz1,1201,227
SVG1,0151,147
3D1,0461,183
Game dev1,0811,194
Agentic game dev—1,113
HTML slides—1,077
Python→PPTX slides—1,167
Code categories1,1001,232
ASCII art1,1231,138
blender3d—1,067
codetovideo—1,210
pdf—1,264
spreadsheet—1,164
Specs
Context window200K524K
Max output tokens64K512K
Input modalitiestext, image, filetext, image, video
TokenizerClaudeOther