[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [Motif 3](https://spiral.ai/integrations/antigravity/motif-3)

# How to Use Motif 3 in Google Antigravity

Motif 3 suits code fixes, terminal troubleshooting, and questions that connect long documents. Its clearest strengths are multi-step tool use and terminal problem solving; specialized scientific coding is less competitive.

|  |  |
| --- | --- |
| Model | Motif 3 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.006404 per run at the default inputs. $0.39 per 1M input tokens, $1.56 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Motif 3 in Google Antigravity

- Use Motif 3 to investigate the failing tests in this repository. Reproduce the failure, trace its cause, make the smallest justified fix, and run the relevant tests. Report the evidence that the fix works.
- Use Motif 3 to trace the login flow through this project's files. Identify where an expired session could cause repeated redirects, explain the evidence, and add a focused regression test with any fix.
- Use Motif 3 to compare this repository's API implementation with its specification. List behavior mismatches with file references, then fix the clearest mismatch and verify it.
- Use Motif 3 to investigate the build failure using terminal output and project configuration. Check one hypothesis at a time, preserve the results, and stop when the build passes or a specific blocker is established.
- Use Motif 3 to review the current diff against the project's requirements. Focus on incorrect behavior and missing tests, cite the relevant code, and distinguish confirmed defects from questions.

## How to set up Motif 3 in Google Antigravity

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

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity 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 Motif 3**: 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": "motif-technologies/motif-3",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds Motif 3 on Spiral, shows the price and runs it.

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

## Motif 3 tools and prices

- [Motif Technologies: Motif 3](https://spiral.ai/tools/openrouter/motif-technologies/motif-3) (OpenRouter): Up to $0.006404 per run at the default inputs. $0.39 per 1M input tokens, $1.56 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| logprobs |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 235929 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |

## What can you do with Motif 3 in Google Antigravity?

Turn a repository issue into a code change checked by tests with Motif 3. Give the agent the failing behavior, relevant project context, and a clear condition for completion.

### Fix a repository issue

Use Motif 3 to trace a reported bug, change the relevant code, and check the result with focused tests.

### Investigate terminal failures

Give Motif 3 command output and a clear success condition. Ask for an investigation that checks each hypothesis against subsequent results.

### Compare long technical documents

Ask Motif 3 to connect requirements across specifications, identify contradictions, and cite the sections behind each finding.

### Answer questions from a policy collection

Provide labeled policy text and ask Motif 3 for evidence-backed answers, with an explicit unknown when the material does not resolve a question.

### Prepare English and Korean support drafts

Use Motif 3 to draft responses from supplied support policies. Specify the output language and preserve product names and technical terms.

### Review changes across recurring reports

Give Motif 3 the previous and current report text. Request a concise account of changed claims, conflicting evidence, and questions that remain unanswered.

### Investigate a support issue with tools

Use Motif 3 to select relevant lookups, interpret returned results, and draft a resolution tied to the supplied policy and evidence.

## Overview

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

## Motif 3 in other agents

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

## More Google Antigravity guides

- [Morph V3 Large (batch)](https://spiral.ai/integrations/antigravity/morph-v3-large-batch)
- [Muse Ember](https://spiral.ai/integrations/antigravity/muse-ember)
- [Morph V3 Large](https://spiral.ai/integrations/antigravity/morph-v3-large)
- [Muse Glimmer 30B](https://spiral.ai/integrations/antigravity/muse-glimmer-30b)
- [Morph V3 Fast Batch](https://spiral.ai/integrations/antigravity/morph-v3-fast-batch)
- [Muse Glimmer 30B (batch)](https://spiral.ai/integrations/antigravity/muse-glimmer-30b-batch)

## Questions about Motif 3 in Google Antigravity

**Can Google Antigravity use Motif 3?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run Motif 3 like any built-in tool.

**How much does Motif 3 cost in Google Antigravity?**

Up to $0.006404 per run at the default inputs. $0.39 per 1M input tokens, $1.56 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need an OpenRouter account to use Motif 3 in Google Antigravity?**

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

**How long does it take to set up Motif 3 in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while Motif 3 runs?**

Motif 3 runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is Motif 3 best suited for?**

Start with tasks involving several tool calls, code changes with tests, or answers assembled from long documents. The maker highlights multi-step execution and terminal problem solving.

**How much context can Motif 3 handle?**

Motif 3 has a native context length of 262,144 tokens. Treat that as the context window, rather than a promise that each answer can reach that length.

**Which languages does Motif 3 emphasize?**

The maker describes Motif 3 as multilingual and specifically highlights English and Korean in its tokenizer design. Specify the response language when your source material mixes languages.

**Which sampling settings should I try first?**

Temperature 1.0 and top-p 0.95 match the maker's evaluation settings. Use them as a starting point for your own checks; the published evaluation does not establish one best setting for every task.

**Where does Motif 3 need closer checking?**

The maker reports weaker results than the strongest compared models on scientific coding and specialized scientific reasoning. For those tasks, request executable checks, stated assumptions, and evidence for conclusions.

