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 4.5Nemotron 3.5 Super VL
Claude Haiku 4.5

Anthropic

Nemotron 3.5 Super VL

NVIDIA

Pricing
Input $/1M$1.00$0.15
Output $/1M$5.00$0.50
Blended $/1M (3:1)$2.00$0.237
Cache read $/1M$0.10$0.02
Cache write $/1M$1.25—
Quality indices
Intelligence Index7.413.6
Coding Index——
Math Index——
Agentic Index——
Speed & latency
Output speed (tok/s)——
Time to first token——
Time to first answer token——
Design Arena (Elo)
Website1,1101,154
UI components1,0881,156
Data viz1,1201,085
SVG1,015—
3D1,0461,111
Game dev1,0811,078
Code categories1,1001,135
ASCII art1,123—
pdf—939
Specs
Context window200K1.05M
Max output tokens64K236K
Input modalitiestext, image, filetext, image, video
TokenizerClaudeOther