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.

Gemini 3.6 FlashGPT-5.4
Gemini 3.6 Flash

Google

GPT-5.4

OpenAI

Pricing
Input $/1M$1.50$2.50
Output $/1M$7.50$15.00
Blended $/1M (3:1)$3.00$5.63
Cache read $/1M$0.15$0.25
Cache write $/1M$0.083
Quality indices
Intelligence Index50.151.4
Coding Index69.271.1
Math Index
Agentic Index38.741.1
Speed & latency
Output speed (tok/s)301152
Time to first token11.80s129.43s
Time to first answer token11.80s129.43s
Benchmarks (Artificial Analysis)
GPQA Diamond92.8%92.0%
Humanity's Last Exam38.3%41.6%
SciCode52.7%56.6%
IFBench73.9%
AA-LCR (Long Context Reasoning)69.7%74.0%
Terminal-Bench Hard57.6%
Terminal-Bench 2.177.5%78.3%
τ²-Bench (Telecom)87.1%
τ³-Bench Banking24.5%30.3%
Design Arena (Elo)
Website1,3321,247
Web apps1,122
Full-stack1,076
Mobile apps1,147
Android native1,020
UI components1,281
Data viz1,268
SVG1,241
3D1,160
Game dev1,298
Godot game dev1,135
Code categories1,245
ASCII art1,241
Specs
Context window1.05M1.05M
Max output tokens66K128K
Input modalitiestext, image, video, file, audiotext, image, file
TokenizerGeminiGPT