NNVIDIA · Released Mar 11, 2026
Nemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- Released
- Mar 11 2026
- Context window
- 262K 236K out
- Input / 1M tokens
- $0.30 from Free
- Output / 1M tokens
- $2.40 from Free
Where to run it
23 providers compared
Free to try on Nvidia, Kilo Gateway, Requesty, AIHubMix, OpenCode +1 more — free endpoints are often limited-time and rate-limited. Cheapest: NanoGPT at $0.05 / $0.25 per 1M input / output tokens — 88% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Nvidiafree · may be limited-time | Free | Free | — | 262K | 236K | 0%24h | Free |
| Kilo Gatewayfree · may be limited-time | Free | Free | — | 262K | 236K | — | Free |
| Requestyfree · may be limited-time | Free | Free | — | 1M | 66K | — | Free |
| AIHubMixfree · may be limited-time | Free | Free | — | 262K | 262K | — | Free |
| OpenCodefree · may be limited-time | Free | Free | Free | 205K | 128K | — | Free |
| Kenarifree · may be limited-time | Free | Free | — | 262K | 262K | — | Free |
| NanoGPTno tool calling | $0.05 | $0.25 | $0.025 | 262K | 16K | — | Cheapest |
| Ollama Cloud | $0.015 | $0.60 | $0.015 | 262K | 66K | — | +61% |
| DeepInfraBF16 | $0.085 | $0.40 | — | 262K | 16K | 100%24h | +64% |
| DekaLLMFP8 | $0.08 | $0.45 | — | 262K | 236K | 99.9%24h | +72% |
| Kilo Gateway | $0.08 | $0.45 | — | 262K | 236K | — | +72% |
| Pioneer | $0.09 | $0.45 | $0.09 | 256K | 32K | — | +80% |
| Kenari | $0.097 | $0.48 | $0.01 | 262K | 262K | — | +93% |
| Requesty | $0.10 | $0.50 | — | 262K | 262K | — | +100% |
| Boundless | $0.12 | $0.52 | $0.06 | 262K | 262K | — | +120% |
| Vercel AI Gatewayno tool calling | $0.15 | $0.65 | — | 256K | 32K | — | +175% |
| Amazon Bedrock | $0.15 | $0.65 | — | 262K | 131K | — | +175% |
| DigitalOcean | $0.30 | $0.65 | $0.06 | 1M | 33K | — | +287% |
| Baseten | $0.30 | $0.75 | $0.06 | 203K | 203K | — | +312% |
| Nebius Token Factory | $0.30 | $0.90 | $0.30 | 262K | 33K | — | +350% |
| Eden AI | $0.30 | $0.90 | $0.30 | 262K | 262K | — | +350% |
| Synthetic | $0.30 | $1.00 | $0.06 | 262K | 66K | — | +375% |
| Cloudflare Workers AI | $0.50 | $1.50 | — | 256K | 256K | — | +650% |
| Thinking Machines | $0.57 | $1.44 | $0.11 | 66K | 66K | — | +687% |
| Perplexity Agent | $0.25 | $2.50 | — | 1M | 32K | — | +713% |
| CrusoeFP8 | $0.30 | $2.40 | $0.15 | 262K | 236K | 100%24h | +725% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nemotron 3 Super. Scores appear here automatically once it does.
Specs
Details
- Model ID
nvidia/nemotron-3-super-120b-a12b- Developer
- NVIDIA
- Release date
- Mar 11, 2026 ·
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- API price
- $0.30 / $2.40 per 1M input / output tokens
- Providers
- 23
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- Yes
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.