[ Models ]

Origin for speed. NextGen for depth.

Two models. One assistant. One API. Compare them, then try in Quark.

Try in Quark API docs

Compare

MMLU: 81.4%
GPQA Diamond: 48.1%
HumanEval: 78.9%
MATH: 74.2%
Context window: 128K
Latency: ~18ms

Origin

High-speed, cost-efficient AI for real-time, low-latency interactions across production workloads.

Context: 128K tokens
Latency: ~18ms
Pricing: $0.20

NextGen

Top-tier intelligence, reasoning depth, and computational efficiency for complex, multi-step tasks.

Context: 1M tokens
Latency: ~20ms
Pricing: $2.00