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.

Mercury 2GPT-5.6 Sol
Mercury 2

Inception

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.25$5.00
Output $/1M$0.75$30.00
Blended $/1M (3:1)$0.375$11.25
Cache read $/1M$0.025$0.50
Cache write $/1M$6.25
Quality indices
Intelligence Index21.458.9
Coding Index31.177.4
Math Index
Agentic Index9.654
Speed & latency
Output speed (tok/s)104570
Time to first token3.40s112.90s
Time to first answer token3.40s112.90s
Benchmarks (Artificial Analysis)
GPQA Diamond77.0%94.1%
Humanity's Last Exam15.5%47.2%
SciCode38.7%56.1%
IFBench69.8%72.7%
AA-LCR (Long Context Reasoning)36.3%73.7%
Terminal-Bench Hard26.5%65.9%
Terminal-Bench 2.127.3%88.0%
τ²-Bench (Telecom)70.8%85.1%
τ³-Bench Banking9.9%33.0%
Design Arena (Elo)
Website1,014
UI components1,013
Data viz1,011
SVG1,024
3D1,043
Game dev1,036
Code categories1,025
ASCII art1,046
Specs
Context window128K1.05M
Max output tokens50K128K
Input modalitiestextfile, image, text
TokenizerOtherGPT