[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [MiniMax M2.7](https://spiral.ai/integrations/instinct/minimax-m2-7)

# How to Use MiniMax M2.7 in Instinct

MiniMax M2.7 suits debugging, code delivery, and repeated revisions to office documents. Compared with MiniMax M2.5, MiniMax reports improved performance on its MMClaw agent evaluation.

|  |  |
| --- | --- |
| Model | MiniMax M2.7 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.004483 per run at the default inputs. $0.273 per 1M input tokens, $1.092 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with MiniMax M2.7 in Instinct

- Every morning, use MiniMax M2.7 to review new events in the connected incident feed. Group related errors, cite event IDs, and propose checks for the highest-impact unresolved issue.
- Each evening, use MiniMax M2.7 to review new failures in the connected test results feed. Group likely shared causes and produce a short investigation queue with supporting evidence.
- Every Monday, use MiniMax M2.7 to review completed runs in the connected experiment tracker. Compare results with the stated baseline and recommend one controlled follow-up.
- Each weekday, use MiniMax M2.7 to review report text newly submitted to the connected review queue. Flag contradictory numbers and unsupported conclusions, citing the relevant passages.
- Every Friday, use MiniMax M2.7 to review unresolved security findings in the connected issue tracker. Identify missing reproduction evidence and draft a verification checklist for each finding.

## How to set up MiniMax M2.7 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 MiniMax M2.7**: 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-m2.7",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds MiniMax M2.7 on Spiral, shows the price and runs it.

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

## MiniMax M2.7 tools and prices

- [MiniMax: MiniMax M2.7](https://spiral.ai/tools/openrouter/minimax/minimax-m2.7) (OpenRouter): Up to $0.306737 per run at the default inputs. $0.78 per 1M input tokens, $2.34 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 M2.7 in Instinct?

Keep incident reviews and experiment follow-ups moving with scheduled MiniMax M2.7 tasks. Have each run produce a bounded report with evidence and a clear next action.

### Production incident investigation

Use MiniMax M2.7 to examine logs, rank possible causes, and propose checks that distinguish them.

### Bug fixes with verification

Ask MiniMax M2.7 to reproduce a failure, propose a focused patch, and verify it with tests.

### Code security review

Have MiniMax M2.7 inspect code for security defects and explain each finding with a concrete failure path.

### Application prototypes

Give MiniMax M2.7 a bounded specification and acceptance criteria for a working application prototype.

### Machine learning experiment review

Use MiniMax M2.7 to examine experiment results, diagnose failures, and propose the next controlled comparison.

### Office document revisions

With document tools, ask MiniMax M2.7 to revise reports or presentations while preserving specified content.

### Spreadsheet model maintenance

With spreadsheet tools, use MiniMax M2.7 to revise assumptions and formulas across several review rounds.

## Overview

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

## MiniMax M2.7 in other agents

- [Amp](https://spiral.ai/integrations/amp/minimax-m2-7)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/minimax-m2-7)
- [Claude](https://spiral.ai/integrations/claude-desktop/minimax-m2-7)
- [Claude Code](https://spiral.ai/integrations/claude-code/minimax-m2-7)
- [Cline](https://spiral.ai/integrations/cline/minimax-m2-7)
- [Codex](https://spiral.ai/integrations/codex/minimax-m2-7)
- [Cursor](https://spiral.ai/integrations/cursor/minimax-m2-7)
- [Devin](https://spiral.ai/integrations/devin/minimax-m2-7)
- [dots](https://spiral.ai/integrations/dots/minimax-m2-7)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/minimax-m2-7)
- [Gemini](https://spiral.ai/integrations/gemini/minimax-m2-7)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/minimax-m2-7)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/minimax-m2-7)
- [goose](https://spiral.ai/integrations/goose/minimax-m2-7)
- [Grok](https://spiral.ai/integrations/grok/minimax-m2-7)
- [Grok Build](https://spiral.ai/integrations/grok-build/minimax-m2-7)
- [Hermes](https://spiral.ai/integrations/hermes/minimax-m2-7)
- [Manus](https://spiral.ai/integrations/manus/minimax-m2-7)
- [Muse](https://spiral.ai/integrations/muse/minimax-m2-7)
- [Muse Code](https://spiral.ai/integrations/muse-code/minimax-m2-7)
- [n8n](https://spiral.ai/integrations/n8n/minimax-m2-7)
- [Notion](https://spiral.ai/integrations/notion/minimax-m2-7)
- [OpenClaw](https://spiral.ai/integrations/openclaw/minimax-m2-7)
- [opencode](https://spiral.ai/integrations/opencode/minimax-m2-7)
- [Perplexity](https://spiral.ai/integrations/perplexity/minimax-m2-7)
- [Raycast](https://spiral.ai/integrations/raycast/minimax-m2-7)
- [VS Code](https://spiral.ai/integrations/vscode/minimax-m2-7)
- [Windsurf](https://spiral.ai/integrations/windsurf/minimax-m2-7)
- [Zapier](https://spiral.ai/integrations/zapier/minimax-m2-7)

## More Instinct guides

- [MiniMax M2.5](https://spiral.ai/integrations/instinct/minimax-m2-5)
- [MiniMax M3](https://spiral.ai/integrations/instinct/minimax-m3)
- [MiMo-V2.6 Flash](https://spiral.ai/integrations/instinct/mimo-v2-6-flash)
- [MiniMax M3 (batch)](https://spiral.ai/integrations/instinct/minimax-m3-batch)
- [MiMo-V2.5-Pro](https://spiral.ai/integrations/instinct/mimo-v2-5-pro)
- [MiniMax M3.1 Flash](https://spiral.ai/integrations/instinct/minimax-m3-1-flash)

## Questions about MiniMax M2.7 in Instinct

**Can Instinct use MiniMax M2.7?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run MiniMax M2.7 like any built-in tool.

**How much does MiniMax M2.7 cost in Instinct?**

Up to $0.004483 per run at the default inputs. $0.273 per 1M input tokens, $1.092 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 MiniMax M2.7 in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs MiniMax M2.7 on its own OpenRouter account.

**How long does it take to set up MiniMax M2.7 in Instinct?**

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

**Does Instinct wait while MiniMax M2.7 runs?**

MiniMax M2.7 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is MiniMax M2.7 good at?**

Its documented uses include debugging, log analysis, software delivery, code security, and machine learning. It also suits office tasks that need several rounds of revision.

**How much context can MiniMax M2.7 handle?**

MiniMax's deployment guide documents 196K tokens per sequence. For long tasks, keep the working context below that limit and request a concise handoff summary between stages.

**Can MiniMax M2.7 work directly with images and video?**

Plan around text and tool results. MiniMax directs projects requiring native multimodal input to MiniMax M3; provide extracted text or a description for M2.7.

**Which generation settings should I start with?**

MiniMax recommends temperature 1.0, top-p 0.95, and top-k 40. Use those as a starting point, then evaluate changes against examples from your actual task.

**Can MiniMax M2.7 revise spreadsheets and presentations?**

Yes, with an agent that supplies document editing tools. MiniMax documents repeated editing of Word, Excel, and PowerPoint content; specify which values, formulas, and sections must stay intact.

