Models

Nemotron 3 Ultra

nvidia ↗ · 1049K ctx · 5 providers · updated 2026-09-19 06:15 UTC

Cheapest
$1.05 via OpenRouter
Avg price
$1.33 /1M
providers
5
Tokens (24h)
807B
Volume (24h)
$0 est.
(3 × $0.600 + $2.40) ÷ 4 = $1.05/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.600, 3:1 $1.05, 1:1 $1.50, output only $2.40 per 1M.

The board shows this model's cheapest measured offer ($1.05/1M); the smaller figure under it is the mean of the 5 offers listed below ($1.33/1M). Add those up and divide — it matches. 24h token volume (807B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter-best OpenRouter $0.600$2.40 API-measured
openrouter Pricebook (LiteLLM) $0.625$3.13 Official list
together_ai Pricebook (LiteLLM) $0.600$3.60 Official list
nebius Pricebook (LiteLLM) $1.00$3.00 Official list
requesty Requesty $1.00$3.00 API-measured

Volume trend

894B 30d d-29 · 733B tokensd-28 · 683B tokensd-27 · 737B tokensd-26 · 835B tokensd-25 · 894B tokensd-24 · 788B tokensd-23 · 767B tokensd-22 · 815B tokensd-21 · 750B tokensd-20 · 776B tokensd-19 · 537B tokensd-18 · 493B tokensd-17 · 493B tokensd-16 · 541B tokensd-15 · 513B tokensd-14 · 523B tokensd-13 · 549B tokensd-12 · 524B tokensd-11 · 569B tokensd-10 · 477B tokensd-9 · 477B tokensd-8 · 514B tokensd-7 · 461B tokensd-6 · 592B tokensd-5 · 470B tokensd-4 · 455B tokensd-3 · 442B tokensd-2 · 554B tokensd-1 · 660B tokensd-0 · 807B tokens

Last 30 days: 733B → 807B (+10%); range 442B–894B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/nemotron-3-ultra-550b-a55b.json. Free reuse requires attribution to tkx.org.

About

Nemotron 3 Ultra is an AI model designed for natural language processing tasks, served by multiple inference providers on AI model marketplaces and listed under the organization tag "NVIDIA".

AI-generated summary from public information — is this yours?

FAQ

How much does Nemotron 3 Ultra cost?

Cheapest measured offer right now: $0.6/1M input, $2.4/1M output via openrouter-best — across 5 tracked providers, refreshed hourly.

Who serves Nemotron 3 Ultra?

5 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is Nemotron 3 Ultra used?

Nemotron 3 Ultra routed 807B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings