[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Nemotron 3 Ultra](https://spiral.ai/integrations/gemini-cli/nemotron-3-ultra)

# How to Use Nemotron 3 Ultra in Gemini CLI

Nemotron 3 Ultra handles complex coding, research synthesis, and planning across long conversations. Its 550B total and 55B active parameters distinguish it from Nemotron 3 Super’s 120B total and 12B active parameters.

|  |  |
| --- | --- |
| Model | Nemotron 3 Ultra |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.012808 per run at the default inputs. $0.78 per 1M input tokens, $3.12 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Nemotron 3 Ultra in Gemini CLI

- Use Nemotron 3 Ultra to investigate the failing tests in this project. Trace the relevant code, propose the smallest justified patch, and add a regression test that fails before the fix.
- Use Nemotron 3 Ultra to review this repository's authentication flow. Map the trust boundaries, cite the relevant code, and rank findings by demonstrated impact.
- Use Nemotron 3 Ultra to plan a migration of this project's database access layer. Identify dependencies, divide the work into testable stages, and define rollback criteria.
- Use Nemotron 3 Ultra to compare the implementation with the specification in this project. Return a table of mismatches with code references and a proposed verification step for each.
- Use Nemotron 3 Ultra to review the numerical calculations in this repository. Check assumptions and edge cases, then add tests for any errors you can reproduce.

## How to set up Nemotron 3 Ultra in Gemini CLI

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Nemotron 3 Ultra**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds Nemotron 3 Ultra on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Nemotron 3 Ultra tools and prices

- [NVIDIA: Nemotron 3 Ultra](https://spiral.ai/tools/openrouter/nvidia/nemotron-3-ultra-550b-a55b) (OpenRouter): Up to $0.011738 per run at the default inputs. $0.65 per 1M input tokens, $2.86 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with Nemotron 3 Ultra in Gemini CLI?

Turn a large codebase and its failure evidence into a concrete repair or migration plan with Nemotron 3 Ultra. Give the agent acceptance criteria so its analysis ends in changes you can test.

### Plan a codebase migration

Compare the current architecture with a proposed replacement, trace dependencies, and draft migration stages with tests and rollback criteria.

### Investigate a software defect

Analyze code and failure logs, propose a cause, and produce a patch with a regression test.

### Reconcile research findings

Compare conflicting sources, separate agreement from disagreement, and write a brief that ties conclusions to evidence.

### Answer questions across long documents

Analyze supplied manuals, policies, or reports and return answers with supporting passages and unresolved questions.

### Review multilingual support cases

Compare English, Spanish, French, or other supported-language conversations against supplied policies and draft responses in the customer's language.

### Check mathematical and scientific arguments

Examine supplied assumptions, calculations, and code; identify gaps and propose checks that could confirm or reject the result.

### Turn operational evidence into an action plan

Combine tool results and incident timelines into ranked hypotheses, verification steps, and a recovery plan.

### Extract structured findings

Convert supplied reports into consistent records of findings, evidence, and missing information for downstream review.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Nemotron 3 Ultra in other agents

- [Amp](https://spiral.ai/integrations/amp/nemotron-3-ultra)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/nemotron-3-ultra)
- [Claude](https://spiral.ai/integrations/claude-desktop/nemotron-3-ultra)
- [Claude Code](https://spiral.ai/integrations/claude-code/nemotron-3-ultra)
- [Cline](https://spiral.ai/integrations/cline/nemotron-3-ultra)
- [Codex](https://spiral.ai/integrations/codex/nemotron-3-ultra)
- [Cursor](https://spiral.ai/integrations/cursor/nemotron-3-ultra)
- [Devin](https://spiral.ai/integrations/devin/nemotron-3-ultra)
- [dots](https://spiral.ai/integrations/dots/nemotron-3-ultra)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/nemotron-3-ultra)
- [Gemini](https://spiral.ai/integrations/gemini/nemotron-3-ultra)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/nemotron-3-ultra)
- [goose](https://spiral.ai/integrations/goose/nemotron-3-ultra)
- [Grok](https://spiral.ai/integrations/grok/nemotron-3-ultra)
- [Grok Build](https://spiral.ai/integrations/grok-build/nemotron-3-ultra)
- [Hermes](https://spiral.ai/integrations/hermes/nemotron-3-ultra)
- [Instinct](https://spiral.ai/integrations/instinct/nemotron-3-ultra)
- [Manus](https://spiral.ai/integrations/manus/nemotron-3-ultra)
- [Muse](https://spiral.ai/integrations/muse/nemotron-3-ultra)
- [Muse Code](https://spiral.ai/integrations/muse-code/nemotron-3-ultra)
- [n8n](https://spiral.ai/integrations/n8n/nemotron-3-ultra)
- [Notion](https://spiral.ai/integrations/notion/nemotron-3-ultra)
- [OpenClaw](https://spiral.ai/integrations/openclaw/nemotron-3-ultra)
- [opencode](https://spiral.ai/integrations/opencode/nemotron-3-ultra)
- [Perplexity](https://spiral.ai/integrations/perplexity/nemotron-3-ultra)
- [Raycast](https://spiral.ai/integrations/raycast/nemotron-3-ultra)
- [VS Code](https://spiral.ai/integrations/vscode/nemotron-3-ultra)
- [Windsurf](https://spiral.ai/integrations/windsurf/nemotron-3-ultra)
- [Zapier](https://spiral.ai/integrations/zapier/nemotron-3-ultra)

## More Gemini CLI guides

- [Nemotron 3 Super](https://spiral.ai/integrations/gemini-cli/nemotron-3-super)
- [Nemotron 3.5 Content Safety](https://spiral.ai/integrations/gemini-cli/nemotron-3-5-content-safety)
- [Nemotron 3 Nano 30B A3B](https://spiral.ai/integrations/gemini-cli/nemotron-3-nano-30b-a3b)
- [Nemotron 3.5 Lightning](https://spiral.ai/integrations/gemini-cli/nemotron-3-5-lightning)
- [MythoMax 13B](https://spiral.ai/integrations/gemini-cli/mythomax-13b)
- [Nemotron 3.5 Super VL](https://spiral.ai/integrations/gemini-cli/nemotron-3-5-super-vl)

## Questions about Nemotron 3 Ultra in Gemini CLI

**Can Gemini CLI use Nemotron 3 Ultra?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Nemotron 3 Ultra like any built-in tool.

**How much does Nemotron 3 Ultra cost in Gemini CLI?**

Up to $0.012808 per run at the default inputs. $0.78 per 1M input tokens, $3.12 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need an OpenRouter account to use Nemotron 3 Ultra in Gemini CLI?**

No. Spiral runs Nemotron 3 Ultra on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Nemotron 3 Ultra in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while Nemotron 3 Ultra runs?**

Nemotron 3 Ultra runs in the background. Gemini CLI starts the run, checks on it and gives you the text, json when it's ready.

**What is Nemotron 3 Ultra good at?**

Use it for tasks that combine planning, code generation, research, and verification. NVIDIA specifically highlights maintaining architectural decisions across coding sessions and reconciling contradictory research evidence.

**How much context can Nemotron 3 Ultra handle?**

NVIDIA documents up to 1 million tokens of context. For document analysis, ask for source labels and supporting passages so you can check the conclusions.

**Which languages does Nemotron 3 Ultra support?**

NVIDIA lists English, French, Spanish, Italian, German, Japanese, Hindi, Korean, Brazilian Portuguese, and Chinese. State the desired answer language explicitly when your source material mixes languages.

**What is the tradeoff with shorter reasoning?**

Nemotron 3 Ultra was trained for regular, medium-effort, and reasoning-off modes. NVIDIA reports approximately 7% lower accuracy for medium-effort reasoning in its Artificial Analysis comparison, so test reduced reasoning on representative tasks before using it for difficult decisions.

**Does Nemotron 3 Ultra know recent events?**

NVIDIA lists May 2026 as its post-training data cutoff. Supply current evidence for newer events and ask it to distinguish source-backed findings from assumptions.

