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 Opus 4.6MiniMax M2.7
Claude Opus 4.6

Anthropic

MiniMax M2.7

MiniMax

Pricing
Input $/1M$5.00$0.25
Output $/1M$25.00$1.00
Blended $/1M (3:1)$10.00$0.438
Cache read $/1M$0.50$0.05
Cache write $/1M$6.25
Quality indices
Intelligence Index37.838.1
Coding Index52.6
Math Index
Agentic Index25.6
Speed & latency
Output speed (tok/s)5459
Time to first token1.89s1.17s
Time to first answer token1.89s42.86s
Benchmarks (Artificial Analysis)
GPQA Diamond84.0%87.4%
Humanity's Last Exam18.6%28.1%
SciCode45.7%47.0%
IFBench44.6%75.7%
AA-LCR (Long Context Reasoning)58.3%68.7%
Terminal-Bench Hard48.5%39.4%
Terminal-Bench 2.155.4%
τ²-Bench (Telecom)84.8%84.8%
τ³-Bench Banking8.9%
Design Arena (Elo)
Website1,3231,272
Web apps1,261
Full-stack1,279
Mobile apps1,280
Android native1,195
UI components1,3361,251
Data viz1,3221,269
SVG1,2741,184
3D1,3351,247
Game dev1,3371,265
Code categories1,3271,266
ASCII art1,2981,182
Specs
Context window1M205K
Max output tokens128K131K
Input modalitiestext, image, filetext
TokenizerClaudeOther