tokenstat
tokenstat

Nemotron 3 Super 120B

workers-ai/@cf/nvidia/nemotron-3-120b-a12b · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.5
$/MTok · models.dev
Cheapest output
$1.50
$/MTok
Context
256K
tokens
Offers
5
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestworkers-ai/@cf/nvidia/nemotron-3-120b-a12bCloudflare$0.5$1.50$0256K
models.dev@cf/nvidia/nemotron-3-120b-a12bCloudflare$0.5$1.50$0256K
LiteLLM@cf/nvidia/nemotron-3-120b-a12b$0.5$1.50$0.05
LiteLLMcloudflare/@cf/nvidia/nemotron-3-120b-a12b$0.5$1.50$0.05
LiteLLMnemotron-3-120b-a12b$0.5$1.50$0.05

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2026-03-11Family: nemotron

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash