[Integrations](https://spiral.ai/integrations) › [Gemini](https://spiral.ai/integrations/gemini) › [Amazon Nova Premier 1.0](https://spiral.ai/integrations/gemini/amazon-nova-premier-1-0)

# How to Use Amazon Nova Premier 1.0 in Gemini

Amazon Nova Premier 1.0 handles questions that span long documents, large codebases, and several sources. Its one-million-token context window helps when a short excerpt leaves out evidence the answer needs.

|  |  |
| --- | --- |
| Model | Amazon Nova Premier 1.0 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.066675 per run at the default inputs. $3.25 per 1M input tokens, $16.25 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Amazon Nova Premier 1.0 in Gemini

- Use Amazon Nova Premier 1.0 to compare the two proposals in this conversation. Return a table of scope, assumptions, dependencies, and unresolved questions, with a supporting passage for each difference.
- Use Amazon Nova Premier 1.0 to summarize the transcript above into decisions, action items, and open questions. Include owners and deadlines only when explicitly stated, and keep the summary under 500 words.
- Use Amazon Nova Premier 1.0 to answer my questions using only the reference passages above. Cite passage labels, explain conflicting evidence, and say when the material does not contain an answer.
- Use Amazon Nova Premier 1.0 to draft a Spanish support reply from the approved policy and customer message above. Preserve the policy's meaning, avoid unsupported promises, and keep the reply under 180 words.
- Use Amazon Nova Premier 1.0 to turn the project brief and dependency notes above into an ordered work plan. For each step, name its prerequisite, expected result, and supporting source.

## How to set up Amazon Nova Premier 1.0 in Gemini

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

### Use the Gemini connector

1. **Open Connected Apps**: On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.

2. **Add Spiral as a custom app**: Under Custom apps, click Add a custom app and paste this MCP server URL:

```text
https://api.spiral.ai/mcp
```

3. **Sign in to Spiral and approve**: Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.

### Use the Spiral skill

1. **Send Gemini 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 Amazon Nova Premier 1.0**: 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": "amazon/nova-premier-v1",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Gemini finds Amazon Nova Premier 1.0 on Spiral, shows the price and runs it.

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

## Amazon Nova Premier 1.0 tools and prices

- [Amazon: Nova Premier 1.0](https://spiral.ai/tools/openrouter/amazon/nova-premier-v1) (OpenRouter): Up to $0.066675 per run at the default inputs. $3.25 per 1M input tokens, $16.25 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 32000 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Amazon Nova Premier 1.0 in Gemini?

Amazon Nova Premier can turn a long conversation or set of documents into a sourced answer, comparison, or work plan. Give it the material to analyze and ask it to distinguish stated facts from unresolved questions.

### Compare lengthy specifications

Use Amazon Nova Premier 1.0 to compare requirements across technical specifications. Request a table of agreements, conflicts, and missing details with a supporting passage for each finding.

### Review changes across a codebase

Use Amazon Nova Premier 1.0 to trace how a proposed change affects callers, shared types, and tests. Ask for a focused patch plan before generating code.

### Answer questions from internal documentation

Give Amazon Nova Premier 1.0 relevant documentation passages and ask for an answer with passage references. Require it to identify questions the supplied material cannot resolve.

### Extract records from business text

Ask Amazon Nova Premier 1.0 to turn order descriptions or service requests into JSON with a defined schema. Validate the records and preserve missing values rather than inventing them.

### Summarize project discussions

Use Amazon Nova Premier 1.0 to turn meeting transcripts and discussion threads into decisions, unresolved questions, and action items. Require evidence for owners and deadlines.

### Prepare a sourced operations brief

Give Amazon Nova Premier 1.0 current incident summaries and operational notes. Request a concise brief that separates reported events, proposed explanations, and follow-up questions.

### Draft multilingual support replies

Use Amazon Nova Premier 1.0 to draft replies in English, German, French, Spanish, Italian, Portuguese, Japanese, Hindi, or Arabic from approved support material. Review the wording before sending.

### Plan work across several sources

Ask Amazon Nova Premier 1.0 to combine a project brief, requirements, and dependency notes into an ordered work plan. Require each proposed step to name its prerequisites and supporting evidence.

## Overview

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

## Amazon Nova Premier 1.0 in other agents

- [Amp](https://spiral.ai/integrations/amp/amazon-nova-premier-1-0)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/amazon-nova-premier-1-0)
- [Claude](https://spiral.ai/integrations/claude-desktop/amazon-nova-premier-1-0)
- [Claude Code](https://spiral.ai/integrations/claude-code/amazon-nova-premier-1-0)
- [Cline](https://spiral.ai/integrations/cline/amazon-nova-premier-1-0)
- [Codex](https://spiral.ai/integrations/codex/amazon-nova-premier-1-0)
- [Cursor](https://spiral.ai/integrations/cursor/amazon-nova-premier-1-0)
- [Devin](https://spiral.ai/integrations/devin/amazon-nova-premier-1-0)
- [dots](https://spiral.ai/integrations/dots/amazon-nova-premier-1-0)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/amazon-nova-premier-1-0)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/amazon-nova-premier-1-0)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/amazon-nova-premier-1-0)
- [goose](https://spiral.ai/integrations/goose/amazon-nova-premier-1-0)
- [Grok](https://spiral.ai/integrations/grok/amazon-nova-premier-1-0)
- [Grok Build](https://spiral.ai/integrations/grok-build/amazon-nova-premier-1-0)
- [Hermes](https://spiral.ai/integrations/hermes/amazon-nova-premier-1-0)
- [Instinct](https://spiral.ai/integrations/instinct/amazon-nova-premier-1-0)
- [Manus](https://spiral.ai/integrations/manus/amazon-nova-premier-1-0)
- [Muse](https://spiral.ai/integrations/muse/amazon-nova-premier-1-0)
- [Muse Code](https://spiral.ai/integrations/muse-code/amazon-nova-premier-1-0)
- [n8n](https://spiral.ai/integrations/n8n/amazon-nova-premier-1-0)
- [Notion](https://spiral.ai/integrations/notion/amazon-nova-premier-1-0)
- [OpenClaw](https://spiral.ai/integrations/openclaw/amazon-nova-premier-1-0)
- [opencode](https://spiral.ai/integrations/opencode/amazon-nova-premier-1-0)
- [Perplexity](https://spiral.ai/integrations/perplexity/amazon-nova-premier-1-0)
- [Raycast](https://spiral.ai/integrations/raycast/amazon-nova-premier-1-0)
- [VS Code](https://spiral.ai/integrations/vscode/amazon-nova-premier-1-0)
- [Windsurf](https://spiral.ai/integrations/windsurf/amazon-nova-premier-1-0)
- [Zapier](https://spiral.ai/integrations/zapier/amazon-nova-premier-1-0)

## More Gemini guides

- [Amazon Nova Micro](https://spiral.ai/integrations/gemini/amazon-nova-micro)
- [Amazon Nova Pro 1.0](https://spiral.ai/integrations/gemini/amazon-nova-pro-1-0)
- [Amazon Nova Lite 1.0](https://spiral.ai/integrations/gemini/amazon-nova-lite-1-0)
- [Beam 1.0 501B A23B](https://spiral.ai/integrations/gemini/beam-1-0-501b-a23b)
- [Amazon Nova 2 Lite](https://spiral.ai/integrations/gemini/amazon-nova-2-lite)
- [Claude Fable 5](https://spiral.ai/integrations/gemini/claude-fable-5)

## Questions about Amazon Nova Premier 1.0 in Gemini

**Can Gemini use Amazon Nova Premier 1.0?**

Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Amazon Nova Premier 1.0 like any built-in tool.

**How much does Amazon Nova Premier 1.0 cost in Gemini?**

Up to $0.066675 per run at the default inputs. $3.25 per 1M input tokens, $16.25 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 plan is separate.

**Do I need an OpenRouter account to use Amazon Nova Premier 1.0 in Gemini?**

No. Spiral runs Amazon Nova Premier 1.0 on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Amazon Nova Premier 1.0 in Gemini?**

About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.

**Does Gemini wait while Amazon Nova Premier 1.0 runs?**

Amazon Nova Premier 1.0 runs in the background. Gemini starts the run, checks on it and gives you the text, json when it's ready.

**What is Amazon Nova Premier 1.0 useful for?**

Use it to answer questions across long documents, review large codebases, and plan tasks that involve several sources. Give it the relevant evidence and a clear description of the result you need.

**How much context and output can Amazon Nova Premier handle?**

Amazon documents a one-million-token context window, and its model specification table lists 10,000 output tokens. For large reports, request an outline first and draft sections separately.

**Does filling the context window improve accuracy?**

More context is not automatically better: AWS says performance can decline as the context grows. Select relevant passages, put source material first, and place your question and instructions at the end.

**Which languages can I use with Amazon Nova Premier?**

AWS lists English, German, French, Spanish, Italian, Portuguese, Japanese, Hindi, and Arabic as generally available languages for Amazon Nova. Review terminology and meaning in the language you plan to publish.

**Can Amazon Nova Premier return dependable JSON?**

Give it an explicit schema and request JSON without introductory text. AWS recommends temperature zero for structured output, but responses can still depart from the schema, so validate them before use.

