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 M2.5
Claude Haiku 4.5

Anthropic

MiniMax M2.5

MiniMax

Pricing
Input $/1M$1.00$0.15
Output $/1M$5.00$0.90
Blended $/1M (3:1)$2.00$0.337
Cache read $/1M$0.10$0.05
Cache write $/1M$1.25
Quality indices
Intelligence Index29.633.7
Coding Index43.9
Math Index
Agentic Index16.4
Speed & latency
Output speed (tok/s)86
Time to first token1.01s
Time to first answer token24.40s
Benchmarks (Artificial Analysis)
GPQA Diamond84.8%
Humanity's Last Exam19.1%
SciCode42.6%
IFBench71.6%
AA-LCR (Long Context Reasoning)66.0%
Terminal-Bench Hard34.8%
τ²-Bench (Telecom)95.3%
Design Arena (Elo)
Website1,1491,249
UI components1,1421,215
Data viz1,1601,208
SVG1,0721,197
3D1,1311,228
Game dev1,1551,235
Code categories1,1481,240
ASCII art1,182
Specs
Context window200K205K
Max output tokens64K197K
Input modalitiestext, image, filetext
TokenizerClaudeOther