WhichAI / Models / Nemotron 3 Ultra

Nemotron 3 Ultra

· verified July 26, 2026

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

Provider

Statuspublic

AA Intelligence Index37.8 (July 16, 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 ≈ 55–60). Snapshot: July 24, 2026 (BenchLM mirror), retrieved July 26, 2026. Context, price and release data come from vendor pages and public pricing mirrors (retrieved July 19, 2026). Missing values are not published or not yet verified - shown as -. Sources are linked inside the app (Model guide and About > Methodology).