[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Amazon Nova Lite 1.0](https://spiral.ai/integrations/instinct/amazon-nova-lite-1-0)

# How to Use Amazon Nova Lite 1.0 in Instinct

Amazon Nova Lite 1.0 suits document summaries, customer questions, and translation where speed matters. Unlike Amazon Nova Micro, it can also understand images and video while returning text.

|  |  |
| --- | --- |
| Model | Amazon Nova Lite 1.0 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001282 per run at the default inputs. $0.078 per 1M input tokens, $0.312 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Amazon Nova Lite 1.0 in Instinct

- Every weekday morning, use Amazon Nova Lite 1.0 to summarize the new support conversations supplied to this task. Return five recurring concerns with a supporting quotation for each, in under 400 words.
- Every hour, use Amazon Nova Lite 1.0 to classify newly supplied tickets as technical issue, billing question, general question, or uncertain. Follow the approved labeled examples and return one result per ticket.
- Each Friday, use Amazon Nova Lite 1.0 to turn the supplied meeting transcripts into a weekly decision digest. Include stated owners and deadlines, and mark either as unstated when absent.
- Each day, use Amazon Nova Lite 1.0 to translate the supplied English service updates into German. Preserve product names and follow the approved terminology list.
- Each evening, use Amazon Nova Lite 1.0 to extract dates, organizations, and commitments from the newly supplied correspondence. Return one JSON object per message and use null for missing information.

## How to set up Amazon Nova Lite 1.0 in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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 Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

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

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 Lite 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-lite-v1",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## Amazon Nova Lite 1.0 tools and prices

- [Amazon: Nova Lite 1.0](https://spiral.ai/tools/openrouter/amazon/nova-lite-v1) (OpenRouter): Up to $0.001282 per run at the default inputs. $0.078 per 1M input tokens, $0.312 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 5120 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Amazon Nova Lite 1.0 in Instinct?

Produce recurring summaries and sort new text records with Amazon Nova Lite 1.0. Keep the instructions and examples consistent across runs so the results are easier to compare.

### Meeting summaries

Turn a meeting transcript into a brief summary, decisions, and action items. Ask for supporting passages beside each decision and leave unstated owners or dates blank.

### Questions about supplied documents

Answer employee or customer questions from supplied policy passages. Request a supporting quotation and an explicit statement when the passages do not contain the answer.

### Support ticket classification

Sort incoming tickets into defined categories using labeled examples. Include an uncertain category for requests that do not clearly match.

### Translation drafts

Translate customer messages or short help articles between optimized languages. Supply a glossary to keep product names and technical terms consistent.

### Small code tasks

Draft a short Python utility, explain a SQL query, or document a TypeScript function. Specify the expected behavior and review the generated code before using it.

### Structured document extraction

Ask for dates, organizations, and stated commitments from supplied text in a fixed JSON structure. Provide an example and require null for missing values.

## Overview

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

## Amazon Nova Lite 1.0 in other agents

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

## More Instinct guides

- [Amazon Nova 2 Lite](https://spiral.ai/integrations/instinct/amazon-nova-2-lite)
- [Amazon Nova Micro](https://spiral.ai/integrations/instinct/amazon-nova-micro)
- [Aion-RP 1.0 (8B)](https://spiral.ai/integrations/instinct/aion-rp-1-0-8b)
- [Amazon Nova Premier 1.0](https://spiral.ai/integrations/instinct/amazon-nova-premier-1-0)
- [Aion 3.5 Mini](https://spiral.ai/integrations/instinct/aion-3-5-mini)
- [Amazon Nova Pro 1.0](https://spiral.ai/integrations/instinct/amazon-nova-pro-1-0)

## Questions about Amazon Nova Lite 1.0 in Instinct

**Can Instinct use Amazon Nova Lite 1.0?**

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

**How much does Amazon Nova Lite 1.0 cost in Instinct?**

Up to $0.001282 per run at the default inputs. $0.078 per 1M input tokens, $0.312 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need an OpenRouter account to use Amazon Nova Lite 1.0 in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Amazon Nova Lite 1.0 on its own OpenRouter account.

**How long does it take to set up Amazon Nova Lite 1.0 in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Amazon Nova Lite 1.0 runs?**

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

**What is Amazon Nova Lite 1.0 good at?**

Document summaries, translation, document questions, and customer conversations are useful starting points. Give it the source material and a narrowly defined task.

**How much context can Amazon Nova Lite 1.0 handle?**

It supports inputs up to 300,000 tokens. For document work, identify the sections and questions that matter so the requested answer stays focused.

**Which languages is Amazon Nova Lite 1.0 optimized for?**

AWS lists English, German, Spanish, French, Italian, Japanese, Korean, Arabic, Simplified Chinese, Russian, Hindi, Portuguese, Dutch, Turkish, and Hebrew.

**Can Amazon Nova Lite 1.0 return JSON?**

You can request JSON in the prompt and specify the exact structure. Include an example showing how to represent missing information.

**Where does Amazon Nova Lite 1.0 need extra context?**

Questions about current events, specialized knowledge, or particular dialects can exceed its training coverage. Supply relevant source passages and ask it to identify unanswered questions.

