ModelPickr

Models / Nvidia / Nemotron 3 Super 120B A12B

Nvidia · nemotron

Nemotron 3 Super 120B A12B

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

$0.20 in · $0.80 out

per 1M tokens · first-party price. Reference price from Nvidia, the lab's own listing.

Provider input prices run from $0.015 to $0.50 per 1M tokens. Output prices run from $0.25 to $2.50.

Context
262,144
Max output
262,144
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Mar 11, 2026
Updated in source
Mar 11, 2026
Knowledge
—
Providers
20

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Ollama Cloud$0.015$0.60$0.015——
NanoGPT$0.05$0.25$0.025——
Kilo Gateway$0.08$0.45———
OpenRouter$0.08$0.45———
Pioneer$0.09$0.45$0.09$0.09—
Amazon Bedrock$0.15$0.65———
Vercel AI Gateway$0.15$0.65———
Nvidiareference$0.20$0.80———
Perplexity Agent$0.25$2.50———
Baseten$0.30$0.75$0.06——
Crusoe$0.30$2.40$0.15——
DigitalOcean$0.30$0.65$0.06——
Eden AI$0.30$0.90$0.30——
Nebius Token Factory$0.30$0.90———
Synthetic$0.30$1.00$0.30——
Cloudflare Workers AI$0.50$1.50———
AIHubMix$0$0———
Kenari$0$0———
OpenCode$0$0$0—deprecated
Requesty$0$0———

Jobs this model qualifies for