[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [MiniMax M3 (batch)](https://spiral.ai/integrations/antigravity/minimax-m3-batch)

# How to Use MiniMax M3 (batch) in Google Antigravity

MiniMax M3 suits repository analysis, bug fixes, and research across long documents. It combines a million-token context window with tool use and optional reasoning for tasks that require several steps.

|  |  |
| --- | --- |
| Model | MiniMax M3 (batch) |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.004697 per run at the default inputs. $0.2912 per 1M input tokens, $1.144 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with MiniMax M3 (batch) in Google Antigravity

- Use MiniMax M3 to investigate the failing tests in this project. Trace the cause across relevant files, make the smallest justified fix, and report the test results.
- Use MiniMax M3 to compare this repository with its migration specification. List affected modules, implementation order, compatibility risks, and acceptance checks.
- Use MiniMax M3 to inspect the slowest operation identified in the profiling logs. Propose one change, verify correctness, and measure performance using the existing benchmark.
- Use MiniMax M3 to trace a request through this project's frontend and backend. Identify mismatched assumptions and propose tests for the boundaries between components.
- Use MiniMax M3 to review the design documents against the implementation. Produce a table of missing behavior with file references and a suggested verification step for each item.

## How to set up MiniMax M3 (batch) 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 MiniMax M3 (batch)**: 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": "minimax/minimax-m3:batch",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds MiniMax M3 (batch) on Spiral, shows the price and runs it.

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

## MiniMax M3 (batch) tools and prices

- [MiniMax: MiniMax M3 (batch)](https://spiral.ai/tools/openrouter/minimax/minimax-m3%3Abatch) (OpenRouter): Up to $0.004697 per run at the default inputs. $0.2912 per 1M input tokens, $1.144 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 MiniMax M3 (batch) in Google Antigravity?

Turn repository context into bug fixes, migration plans, and measured performance changes with MiniMax M3. Give the agent a reproduction and acceptance checks so it can carry the task through to a reviewable result.

### Trace a bug across a repository

Follow an error from its entry point through related modules, propose a focused patch, and check it against a reproduction.

### Plan a code migration

Compare existing code with a target specification, identify affected components, and produce an ordered migration plan with acceptance checks.

### Investigate a performance bottleneck

Review code and profiling evidence, propose a measurable change, and compare correctness and timing before accepting it.

### Compare long technical documents

Build a requirements matrix across specifications, flag contradictions, and cite the sections behind each finding.

### Prepare a research brief

Use search results and source material to answer a narrow question, explain disagreements, and list evidence that remains missing.

### Turn operational records into a report

Combine supplied status updates, incident timelines, and action lists into a concise report with owners and unresolved issues.

## Overview

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

## MiniMax M3 (batch) in other agents

- [Amp](https://spiral.ai/integrations/amp/minimax-m3-batch)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/minimax-m3-batch)
- [Claude](https://spiral.ai/integrations/claude-desktop/minimax-m3-batch)
- [Claude Code](https://spiral.ai/integrations/claude-code/minimax-m3-batch)
- [Cline](https://spiral.ai/integrations/cline/minimax-m3-batch)
- [Codex](https://spiral.ai/integrations/codex/minimax-m3-batch)
- [Cursor](https://spiral.ai/integrations/cursor/minimax-m3-batch)
- [Devin](https://spiral.ai/integrations/devin/minimax-m3-batch)
- [dots](https://spiral.ai/integrations/dots/minimax-m3-batch)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/minimax-m3-batch)
- [Gemini](https://spiral.ai/integrations/gemini/minimax-m3-batch)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/minimax-m3-batch)
- [goose](https://spiral.ai/integrations/goose/minimax-m3-batch)
- [Grok](https://spiral.ai/integrations/grok/minimax-m3-batch)
- [Grok Build](https://spiral.ai/integrations/grok-build/minimax-m3-batch)
- [Hermes](https://spiral.ai/integrations/hermes/minimax-m3-batch)
- [Instinct](https://spiral.ai/integrations/instinct/minimax-m3-batch)
- [Manus](https://spiral.ai/integrations/manus/minimax-m3-batch)
- [Muse](https://spiral.ai/integrations/muse/minimax-m3-batch)
- [Muse Code](https://spiral.ai/integrations/muse-code/minimax-m3-batch)
- [n8n](https://spiral.ai/integrations/n8n/minimax-m3-batch)
- [Notion](https://spiral.ai/integrations/notion/minimax-m3-batch)
- [OpenClaw](https://spiral.ai/integrations/openclaw/minimax-m3-batch)
- [opencode](https://spiral.ai/integrations/opencode/minimax-m3-batch)
- [Perplexity](https://spiral.ai/integrations/perplexity/minimax-m3-batch)
- [Raycast](https://spiral.ai/integrations/raycast/minimax-m3-batch)
- [VS Code](https://spiral.ai/integrations/vscode/minimax-m3-batch)
- [Windsurf](https://spiral.ai/integrations/windsurf/minimax-m3-batch)
- [Zapier](https://spiral.ai/integrations/zapier/minimax-m3-batch)

## More Google Antigravity guides

- [MiniMax M3](https://spiral.ai/integrations/antigravity/minimax-m3)
- [MiniMax M3.1 Flash](https://spiral.ai/integrations/antigravity/minimax-m3-1-flash)
- [MiniMax M2.7](https://spiral.ai/integrations/antigravity/minimax-m2-7)
- [Ministral 3 14B](https://spiral.ai/integrations/antigravity/ministral-3-14b)
- [MiniMax M2.5](https://spiral.ai/integrations/antigravity/minimax-m2-5)
- [Ministral 3 3B](https://spiral.ai/integrations/antigravity/ministral-3-3b)

## Questions about MiniMax M3 (batch) in Google Antigravity

**Can Google Antigravity use MiniMax M3 (batch)?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run MiniMax M3 (batch) like any built-in tool.

**How much does MiniMax M3 (batch) cost in Google Antigravity?**

Up to $0.004697 per run at the default inputs. $0.2912 per 1M input tokens, $1.144 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 MiniMax M3 (batch) in Google Antigravity?**

No. Spiral runs MiniMax M3 (batch) on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up MiniMax M3 (batch) in Google Antigravity?**

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

**Does Google Antigravity wait while MiniMax M3 (batch) runs?**

MiniMax M3 (batch) runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is MiniMax M3 good at?**

MiniMax M3 is suited to bug fixing, frontend and backend development, performance optimization, and research that involves search. Give it a concrete deliverable, supporting evidence, and a way to check the result.

**How much context can MiniMax M3 handle?**

MiniMax documents a 1,000,000-token context window. That makes large document collections and repository analysis practical uses; ask for source references so you can check which material supports each conclusion.

**How long can MiniMax M3's output be?**

MiniMax's completion documentation specifies a maximum generation allowance of 524,288 tokens and recommends 131,072 tokens. Treat those as maker specifications; request a bounded deliverable such as a patch, a comparison table, or a report with a defined length.

**Which sampling settings does MiniMax recommend?**

The model card recommends temperature 1.0 and top_p 0.95. MiniMax's current documentation says its Anthropic-compatible interface fixes those values, so do not assume changing them will change the result.

**Where does MiniMax M3 still need careful checking?**

Difficult kernel optimization needs measured validation: MiniMax reports 28.8% on KernelBench Hard. For that work, require correctness checks and reproducible timing results before accepting a change.

