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.

Nemotron 3.5 Super VLGPT-5.6 Sol
Nemotron 3.5 Super VL

NVIDIA

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$0.15$4.00
Output $/1M$0.50$20.00
Blended $/1M (3:1)$0.237$8.00
Cache read $/1M$0.02$0.40
Cache write $/1M—$5.00
Quality indices
Intelligence Index13.6—
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,154—
UI components1,156—
Data viz1,085—
3D1,111—
Game dev1,078—
Code categories1,135—
pdf939—
Specs
Context window1.05M1.05M
Max output tokens236K128K
Input modalitiestext, image, videofile, image, text
TokenizerOtherGPT