Nemotron 3 Ultra
TL;DR
Open-sourceOpen reasoning model for long-horizon autonomous agents.
Available on
Routed across multiple upstream providers; price matches the Command Code pricing page.
Switch with
Pick Nemotron 3 Ultra from the selector.
Input
$0.60
per M tokens
Output
$2.40
per M tokens
Cache read
$0.12
per M tokens
Nemotron 3 Ultra in Command Code
Nemotron 3 Ultra is NVIDIA's open reasoning model (550B total parameters, 55B active) — built for long-horizon autonomous agents, with a 1M-token context window. A large mixture-of-experts model at a low per-token price.
Nemotron 3 Ultra vs the Command Code lineup
Pricing for Nemotron 3 Ultra alongside the most relevant peers. Nemotron 3 Ultra is not yet on the Intelligence Index; benchmarked peers show their scores.
| Model | Intelligence | Speed | Input $/M | Output $/M |
|---|---|---|---|---|
| Nemotron 3 Ultra | Not yet scored | — | $0.60 | $2.40 |
| DeepSeek V4 Pro | 52 | ~35 tok/s | $0.435 | $0.87 |
| GLM-5 | 50 | ~61 tok/s | $1.00 | $3.20 |
| Kimi K2.6 | 54 | ~40 tok/s | $0.95 | $4.00 |
| MiniMax M3 | Not yet scored | — | $0.30 | $1.20 |
| Claude Sonnet 4.6 | 52 | ~62 tok/s | $3.00 | $15.00 |
What Nemotron 3 Ultra is best for
Long-horizon autonomous agent runs, reasoning-heavy multi-step tasks, and large-context work up to 1M tokens at open-source prices.
When to switch away from Nemotron 3 Ultra
Switch to DeepSeek V4 Pro
For benchmarked long-context hybrid-attention reasoning (Intelligence Index 52).
Switch to Kimi K2.6
For the top-ranked open-weights model (Intelligence Index 54).
Switch to GLM-5
For a benchmarked middleweight (Intelligence Index 50) at a similar price.
In Command Code: caching and taste-1
Open-source models are routed across multiple upstream providers for high availability. The price you see is the mean per-provider rate; the Usage page reflects what was actually charged.
Where supported by the upstream, prompt caching is on by default — cache reads are billed at $0.12 per million tokens versus $0.60 for fresh input.
taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
Open-source model. Available on every plan, including Go ($1/mo). Routed across multiple upstream providers; listed price matches the Command Code pricing page.
All Command Code models, ranked by quality and speed
Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is reported output tokens per second. Models without a published score are noted.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| GPT-5.5 | Premium | 60 | ~65 tok/s |
| Claude Opus 4.7 | Premium | 57 | ~49 tok/s |
| GPT-5.4 | Premium | 57 | ~84 tok/s |
| GPT-5.3 Codex | Premium | 54 | ~72 tok/s |
| Kimi K2.6 | Open-source | 54 | ~40 tok/s |
| Claude Sonnet 4.6 | Premium | 52 | ~62 tok/s |
| DeepSeek V4 Pro | Open-source | 52 | ~35 tok/s |
| GLM-5 | Open-source | 50 | ~61 tok/s |
| GPT-5.4 Mini | Premium | 49 | ~164 tok/s |
| DeepSeek V4 Flash | Open-source | 47 | ~82 tok/s |
| Claude Haiku 4.5 | Premium | 37 | ~97 tok/s |
| Kimi K2.5 | Open-source | 37 | ~35 tok/s |
| Claude Sonnet 5 | Premium | Not yet scored | — |
| Claude Opus 4.8 | Premium | Not yet scored | — |
| Claude Opus 4.6 | Premium | Not yet scored | — |
| MiniMax M2.5 | Open-source | Not yet scored | — |
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick the model you want and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.
cmd # start an interactive session
/model # open the selector and pick a modelPlans and pricing
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits. Credits roll over and never expire. Auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams | $40 / seat | Pooled | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Frequently asked questions
What does "550b-a55b" mean?
It is a 550-billion-parameter mixture-of-experts model with 55 billion active parameters per token — frontier-class capacity at a lower serving cost, reflected in the price.
Why no Intelligence Index for Nemotron 3 Ultra?
Public aggregate benchmarks have not yet been published for Nemotron 3 Ultra in the current Intelligence Index format. The model is available and routed normally.
Which Command Code model should I use?
For open models, Kimi, DeepSeek, Qwen, Mimo are all really good. For closed models, Claude Sonnet 5 is the recommended default — the best combination of speed and intelligence, and a drop-in upgrade from Sonnet 4.6. Switch to Claude Opus 4.8 (the newest Anthropic flagship) for the most capable long-horizon agentic coding, GPT-5.5 (Intelligence Index 60) for the absolute hardest reasoning, or Claude Opus 4.7 / GPT-5.4 (both 57) for top-tier work at lower cost. For fast lookups, Claude Haiku 4.5 or GPT-5.4 Mini. For open-source, Kimi K2.6 leads the open-weights tier (Intelligence Index 54).
Can I mix Nemotron 3 Ultra with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep Sonnet 5 as the default and switch up to Opus 4.8 or down to Haiku 4.5 as the task calls for it.
Are open-source model prices fixed?
Open-source models are routed across multiple upstream providers for high availability. The price listed for each is the mean per-provider rate. Actual cost on a given request may vary slightly. The Usage page reflects the price charged.
Is Command Code free to try?
The Go plan starts at $1/mo with $10 in LLM credits. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
Does Command Code train on my code?
No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.
Where can I track my usage?
The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.
Does Command Code replace my editor?
No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).
Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.