Skip to content
Sovyron

Nemotron 3 Super 120B

nemotron1.0M context256k max outputreleased Mar 11, 2026Open weightsReasoningTool calling

As of Oct 4, 2026, the cheapest Nemotron 3 Super 120B API price is $0.05 per 1M input tokens (NanoGPT) and $0.25 per 1M output tokens (NanoGPT). Nemotron 3 Super 120B is offered by 3 providers in the nemotron family, open weights, reasoning enabled.

Cheapest input
$0.05
NanoGPT
Cheapest output
$0.25
NanoGPT
Official
—
output per 1M tokens
Providers
3
offering this model
Spread
10.0×
max / min output

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 Super 120B API prices by provider in USD per 1M tokens, updated Oct 4, 2026
Provider1M input1M output1M cache read1M cache writeContext
NanoGPTopenCheapest$0.05Cheapest$0.25$0.025—262k
Cloudflare Workers AIopen$0.5$1.5——256k
Perplexity Agentopen$0.25$2.5——1.0M

Nemotron 3 Super 120B pricing FAQ

What is the cheapest Nemotron 3 Super 120B API?

As of Oct 4, 2026, NanoGPT has the lowest Nemotron 3 Super 120B output price at $0.25 per 1M tokens, and NanoGPT has the lowest input price at $0.05 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer Nemotron 3 Super 120B?

3 providers list Nemotron 3 Super 120B on Sovyron; 3 of them sell it at a metered per-token price.

Is Nemotron 3 Super 120B free?

No provider in the Sovyron catalog lists a free tier for Nemotron 3 Super 120B.

What is the context window of Nemotron 3 Super 120B?

Nemotron 3 Super 120B supports a 1.0M-token context window and up to 256k output tokens.