[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Amazon Nova Pro 1.0](https://spiral.ai/integrations/opencode/amazon-nova-pro-1-0)

# How to Use Amazon Nova Pro 1.0 in opencode

Amazon Nova Pro 1.0 handles document questions, code generation, and image or video analysis. Its 300,000-token context suits tasks that need many source passages in one request.

|  |  |
| --- | --- |
| Model | Amazon Nova Pro 1.0 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.017077 per run at the default inputs. $1.04 per 1M input tokens, $4.16 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Amazon Nova Pro 1.0 in opencode

- Use Amazon Nova Pro 1.0 to read this project's README and public TypeScript exports. Draft a usage guide with three examples using only exports that exist, and cite the relevant file paths.
- Use Amazon Nova Pro 1.0 to inspect the Python function I selected and its callers. Explain its inputs, outputs, and error paths, then draft tests for the documented behavior without changing the implementation.
- Use Amazon Nova Pro 1.0 to compare the SQL schema and migration files in this project. List naming and type differences with file references, and mark anything that cannot be resolved from those files.
- Use Amazon Nova Pro 1.0 to extract the documented HTTP routes from this project's source. Return JSON only with method, path, source_file, and description for each route; use temperature 0 and validate the JSON.
- Use Amazon Nova Pro 1.0 to draft a TypeScript parser for the sample records in this project. First summarize the observed record shapes, then implement the parser and run the project's relevant checks.

## How to set up Amazon Nova Pro 1.0 in opencode

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

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode 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 Pro 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-pro-v1",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## Amazon Nova Pro 1.0 tools and prices

- [Amazon: Nova Pro 1.0](https://spiral.ai/tools/openrouter/amazon/nova-pro-v1) (OpenRouter): Up to $0.017077 per run at the default inputs. $1.04 per 1M input tokens, $4.16 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 Pro 1.0 in opencode?

Turn project code and documentation into focused code drafts, explanations, and source-based answers with Amazon Nova Pro 1.0. Define a small task and an explicit output so you can review the result against the project.

### Questions across long documents

Ask Amazon Nova Pro 1.0 to compare supplied policies or research passages, identify disagreements, and quote the evidence behind each finding.

### Code drafts and explanations

Use Amazon Nova Pro 1.0 to draft Python, TypeScript, or SQL from a precise requirement, then review and test the result in the project.

### Support request classification

Give Amazon Nova Pro 1.0 a fixed set of categories and ask it to label each request, with a short supporting excerpt.

### Structured information extraction

Turn supplied correspondence into JSON records with Amazon Nova Pro 1.0. Define the schema and require null for information the source does not contain.

### Multilingual copy drafts

Ask Amazon Nova Pro 1.0 for English, Spanish, French, or Japanese product copy based on supplied specifications, preserving measurements and product names.

### Image comparisons

Have Amazon Nova Pro 1.0 describe supplied product images and list visible differences, keeping observations separate from guesses.

### Video scene summaries

Use Amazon Nova Pro 1.0 to summarize the broad sequence of visible events in a product demonstration. Check brief actions separately because frame sampling can miss them.

### Answers from approved references

Give Amazon Nova Pro 1.0 relevant help articles and a customer question. Request an answer supported by those articles and a clear statement when the answer is missing.

## Overview

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

## Amazon Nova Pro 1.0 in other agents

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

## More opencode guides

- [Amazon Nova Premier 1.0](https://spiral.ai/integrations/opencode/amazon-nova-premier-1-0)
- [Beam 1.0 501B A23B](https://spiral.ai/integrations/opencode/beam-1-0-501b-a23b)
- [Amazon Nova Micro](https://spiral.ai/integrations/opencode/amazon-nova-micro)
- [Claude Fable 5](https://spiral.ai/integrations/opencode/claude-fable-5)
- [Amazon Nova Lite 1.0](https://spiral.ai/integrations/opencode/amazon-nova-lite-1-0)
- [Claude Fable 5.1](https://spiral.ai/integrations/opencode/claude-fable-5-1)

## Questions about Amazon Nova Pro 1.0 in opencode

**Can opencode use Amazon Nova Pro 1.0?**

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

**How much does Amazon Nova Pro 1.0 cost in opencode?**

Up to $0.017077 per run at the default inputs. $1.04 per 1M input tokens, $4.16 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need an OpenRouter account to use Amazon Nova Pro 1.0 in opencode?**

No. Spiral runs Amazon Nova Pro 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 Pro 1.0 in opencode?**

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

**Does opencode wait while Amazon Nova Pro 1.0 runs?**

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

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

Use it to answer questions about source material, generate code, classify text, and analyze images or videos. It produces text, so visual analysis can become a written summary, comparison, or extraction.

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

It has a 300,000-token context window. For large document tasks, state the question clearly and ask it to use only the supplied sources.

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

Yes. Provide the exact schema, request JSON without introductory text, and use temperature 0 for structured output. Validate the result before another process consumes it.

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

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

**What can Amazon Nova Pro 1.0 miss in a video?**

Its base sampling rate is one frame per second, so it can miss brief events and fast motion. Use it for broad scene summaries rather than treating its answer as a complete account of every frame.

