Nemotron models tuned for efficient reasoning on accelerated infrastructure. NVIDIA’s coding models on Kilo Code include Nemotron 3 Super (free), Nemotron 3 Ultra, and Nemotron 3 Ultra (free). Use them across VS Code, JetBrains IDEs, Cursor, Windsurf, Trae, and the Kilo CLI — with pay-as-you-go pricing and no markup over the underlying provider rates.
Sorted by coding-index where published. Click any model for the full review with benchmarks, real-world Kilo usage, and provider-specific pricing.
NVIDIA
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...
NVIDIA
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA’s Nemotron line reflects the company’s hardware-plus-model approach: models are optimized for fast inference on GPU infrastructure and often released with permissive options for enterprise deployment. For coding, Nemotron is useful when throughput, cost, and deployability matter as much as benchmark rank.
Pay-as-you-go, no markup over the underlying provider rates. Cheapest first.
| Model | Input / 1M | Output / 1M | Context | Coding index |
|---|---|---|---|---|
| NVIDIA: Nemotron 3 Super (free) | Free | Free | 1000K | — |
| NVIDIA: Nemotron 3 Ultra (free) | Free | Free | 1000K | — |
| NVIDIA: Nemotron 3 Ultra | $0.500 | $2.20 | 1000K | — |
Three ways: hosted in Kilo, locally on your hardware, or through your own provider keys.
The fastest path: install Kilo Code, sign in, pick nvidia from the model picker. No API keys, no markup. Works in VS Code, JetBrains, Cursor, Windsurf, Trae, and the Kilo CLI.
See live model leaderboard →Already have an account with NVIDIA, OpenRouter, AWS Bedrock, Google Vertex, Together AI, or another compatible provider? Plug your key into Kilo Code and keep your existing billing relationship.
BYOK setup guide →Download NVIDIA open weights from Hugging Face and serve them with Ollama, LM Studio, vLLM, or SGLang. Connect Kilo Code to your local OpenAI-compatible endpoint and keep all prompts on hardware you control.
Local setup guide →See coding-model lineups from NVIDIA’s closest competitors.
NVIDIA’s flagship is among the strongest coding models on the Kilo Code leaderboard, ranked by Code, Plan, Ask, Debug, and Review usage.
VS Code, Cursor, Windsurf, Trae, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand, RubyMine, Android Studio), and the Kilo CLI / terminal.
Switch between NVIDIA and 500+ other models with one click. Pay only for what you use, at the underlying provider rate.
Nemotron Ultra is generally the strongest NVIDIA option, while Nemotron Super targets a more efficient price/performance point.
NVIDIA models work in all Kilo-supported IDEs and the CLI; downloadable variants can also run on compatible local or self-hosted GPU infrastructure.
NVIDIA model pricing varies by hosted provider, with some free variants available. Kilo Code shows the current token rates with no markup.
Mixed. NVIDIA publishes several Nemotron models for download, while hosted variants may have provider-specific terms.
Ultra variants emphasize capability and reasoning depth. Super variants usually trade some maximum quality for speed and lower serving cost.
NVIDIA models work in all Kilo-supported IDEs and the CLI; downloadable variants can also run on compatible local or self-hosted GPU infrastructure.
Install Kilo Code and get instant access to NVIDIA: Nemotron 3 Super (free) and 2 other NVIDIA models, plus 500+ frontier and open-source options. Free to start, no credit card required.