WhichAI / Models / Nemotron 3 Ultra

Nemotron 3 Ultra

· verified September 8, 2026

public free open-weights api in Generator auto-run speed value reasoning

Provider

Statuspublic

AA Intelligence Index37.8 (September 8, 2026 snapshot)

Releasedn/a

Context window1M

Modalitiesn/a

API price $/1M (in / out)n/a

Speed400+ tok/s on some hosts

AccessFREE on OpenRouter (nvidia/nemotron-3-ultra-550b-a55b:free - WhichAI default runner) · open weights · Perplexity Pro

In one line

Strongest US open model and extremely fast (400+ tokens/second on some hosts) - and genuinely free via OpenRouter.

Coding68

Reasoning68

Writing58

Agents & tools62

Category scores (0-100) are WhichAI blended ratings: public category leaderboards plus editorial judgment. Guidance, not official measurements.

Alternatives worth a look

Grok 4.3 (xAI) · AA 37.6grok.com paid tiers · API
MiniMax M2.7 (MiniMax) · AA 38.1Open weights · API hosts
GPT-5.4 nano (OpenAI) · AA 38.2API (cheapest OpenAI tier)

Head-to-head: Nemotron 3 Ultra vs Inkling

Open Nemotron's official app ↗ Open in the WhichAI app Not sure? Take the 30-second finder

Artificial Analysis Intelligence Index, 2026 rebased scale (top models ~ 55-66). Snapshot: September 4, 2026 (BenchLM mirror), retrieved September 8, 2026. Specs and prices come from the OpenRouter public model list on the same date. Models nobody has measured carry no index score at all and never enter a ranking: where an estimate exists it is shown separately and labelled unmeasured. Context, price, modality and release dates come from the public OpenRouter model list (retrieved September 8, 2026) and vendor pages. Missing values are not published or not yet verified - shown as -. Sources are linked inside the app (Model guide and About > Methodology).