Nemotron 3 Super 120B A12BOpen weights
NVIDIA · released 2026-03-11
No price from the maker itself is on record for Nemotron 3 Super 120B A12B. The lowest of 18 providers is NanoGPT: $0.05 per 1M input tokens and $0.25 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 262K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestnvidia/ | $0.05 | $0.25 | $0.025 | Lowest | Official docs |
NNanoGPTnvidia/ | $0.05 | $0.25 | $0.025 | Official docs | |
EEden AIdeepinfra/ | $0.075 | $0.4 | — | Official docs | |
KKilo Gatewaynvidia/ | $0.075 | $0.4 | — | Official docs | |
 OpenRouternvidia/ | $0.075 | $0.4 | — | Official docs | |
KKenarinemotron-3-super-120b-a12b | $0.097143 | $0.48 | $0.009714 | Official docs | |
RRequestynvidia-nemotron-3-super-120b-a12b | $0.1 | $0.5 | — | Official docs | |
 Ollama Cloudnemotron-3-super | $0.015 | $0.6 | $0.015 | Official docs | |
BBoundlessnemotron3-super | $0.12 | $0.52 | $0.06 | Official docs | |
 Amazon Bedrocknvidia. | $0.15 | $0.65 | — | Official docs | |
 Vercel AI Gatewaynvidia/ | $0.15 | $0.65 | — | Official docs | |
EEden AInebius/ | $0.3 | $0.9 | $0.3 | Official docs |
12 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Nebius Token Factorynvidia/ | $0.3 | $0.9 | $0.06 | Official docs | |
EEden AIarkanecloud/ | $0.4 | $0.8 | $0.1 | Official docs | |
SSynthetichf: | $0.3 | $1 | $0.06 | Official docs | |
TThinking Machinesnvidia/ | $0.57 | $1.44 | $0.114 | Official docs | |
TThinking Machinesnvidia/ | $0.57 | $1.44 | $0.114 | Official docs | |
 Crusoenvidia/ | $0.3 | $2.4 | $0.15 | Official docs | |
 Cloudflare Workers AIDeprecated@cf/ | $0.5 | $1.5 | — | Deprecated | Official docs |
PPerplexity AgentDeprecatednvidia/ | $0.25 | $2.5 | — | Deprecated | Official docs |
 AIHubMixnemotron-3-super-120b-a12b-free | $0 | $0 | — | Official docs | |
KKenarinemotron-3-super-120b-a12b: | $0 | $0 | — | Official docs | |
 OpenCodeDeprecatednemotron-3-super-free | $0 | $0 | $0 | Deprecated | Official docs |
RRequestynemotron-3-super-120b-a12b | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 262K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-06
- Open weights
- Yes
- Released
- 2026-03-11
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.