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 M2.7
Claude Haiku 4.5

Anthropic

MiniMax M2.7

MiniMax

Pricing
Input $/1M$1.00$0.25
Output $/1M$5.00$1.00
Blended $/1M (3:1)$2.00$0.438
Cache read $/1M$0.10$0.05
Cache write $/1M$1.25
Quality indices
Intelligence Index29.638.1
Coding Index43.952.6
Math Index
Agentic Index16.425.6
Speed & latency
Output speed (tok/s)59
Time to first token1.17s
Time to first answer token42.86s
Benchmarks (Artificial Analysis)
GPQA Diamond87.4%
Humanity's Last Exam28.1%
SciCode47.0%
IFBench75.7%
AA-LCR (Long Context Reasoning)68.7%
Terminal-Bench Hard39.4%
Terminal-Bench 2.155.4%
τ²-Bench (Telecom)84.8%
τ³-Bench Banking8.9%
Design Arena (Elo)
Website1,1491,272
UI components1,1421,251
Data viz1,1601,269
SVG1,0721,184
3D1,1311,247
Game dev1,1551,265
Code categories1,1481,266
ASCII art1,1821,182
Specs
Context window200K205K
Max output tokens64K131K
Input modalitiestext, image, filetext
TokenizerClaudeOther