Skip to content
Sovyron

Nemotron 3 Ultra

nemotron1.0M context262k max outputreleased Jun 4, 2026Open weightsReasoningTool calling

As of Oct 4, 2026, the cheapest Nemotron 3 Ultra API price is $0.1 per 1M input tokens (Ollama Cloud) and $1.7 per 1M output tokens (DigitalOcean). Nemotron 3 Ultra is offered by 10 providers in the nemotron family, open weights, reasoning enabled. 4 providers list it as a free-tier offer.

Cheapest input
$0.1
Cheapest output
$1.7
Official
—
output per 1M tokens
Providers
10
offering this model
Spread
1.8×
max / min output
Free offers
4
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

Nemotron 3 Ultra API prices by provider in USD per 1M tokens, updated Oct 4, 2026
Ollama CloudopenCheapest$0.1$3$0.1—262k—
CoreWeaveopen$0.5$2.15$0.1—262k19d agoout −21.8%
Requesty$0.5$2.5——262k—
Vercel AI Gatewayopen$0.6$2.4$0.12—1.0M—
DigitalOcean$0.9Cheapest$1.7$0.18—131k—
Venice AIopen$0.625$3.125$0.1875—256k—
Bothubfreefreefree——1.0M—
Kilo Gatewayfreefreefree——1.0M—
OpenCode Zenfreefreefreefree—1.0M—
OpenRouterfreefreefree——1.0M—

Nemotron 3 Ultra pricing FAQ

What is the cheapest Nemotron 3 Ultra API?

As of Oct 4, 2026, DigitalOcean has the lowest Nemotron 3 Ultra output price at $1.7 per 1M tokens, and Ollama Cloud has the lowest input price at $0.1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Nemotron 3 Ultra?

10 providers list Nemotron 3 Ultra on Sovyron; 6 of them sell it at a metered per-token price.

Is Nemotron 3 Ultra free?

4 provider(s) list a free-tier offer: Bothub, Kilo Gateway, OpenCode Zen, OpenRouter. Free tiers usually have rate limits.

What is the context window of Nemotron 3 Ultra?

Nemotron 3 Ultra supports a 1.0M-token context window and up to 262k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not.

Estimated

—