[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [MiniMax M3.1 Flash](https://spiral.ai/integrations/instinct/minimax-m3-1-flash)

# How to Use MiniMax M3.1 Flash in Instinct

MiniMax M3.1 Flash is built for coding, code security reviews, and tasks that need several tool calls. It combines a context window of up to 1 million tokens with adjustable thinking depth for long documents and complex work.

|  |  |
| --- | --- |
| Model | MiniMax M3.1 Flash |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.78 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 M3.1 Flash in Instinct

- Every weekday, use MiniMax M3.1 Flash to review updates available through the task tools. Summarize changed deadlines, new blockers, and ownership gaps since the previous run. Include a source link for each change.
- Each Monday, use MiniMax M3.1 Flash to compare the current project status with the previous week's report. Identify conflicting updates and overdue dependencies, then prepare a handoff under 500 words.
- Each morning, use MiniMax M3.1 Flash to research changes to the technical standards on my watchlist using available search tools. Include only dated, source-backed changes and explain which need review.
- Every Friday, use MiniMax M3.1 Flash with deeper thinking to compare the current procedures available through the knowledge tools. Flag contradictory instructions with supporting passages and draft a decision list.
- After each scheduled test run, use MiniMax M3.1 Flash to analyze the results supplied by the testing tool. Group related failures, distinguish observed evidence from suspected causes, and prepare an investigation checklist.

## How to set up MiniMax M3.1 Flash 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 M3.1 Flash**: 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-m3.1-flash",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds MiniMax M3.1 Flash on Spiral, shows the price and runs it.

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

## MiniMax M3.1 Flash tools and prices

- [MiniMax: MiniMax M3.1 Flash](https://spiral.ai/tools/openrouter/minimax/minimax-m3.1-flash) (OpenRouter): Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.78 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 M3.1 Flash in Instinct?

Keep recurring research and operations reviews moving with MiniMax M3.1 Flash. Define the reporting period, evidence requirements, and exact deliverable so each run produces a useful comparison.

### Investigate and fix a bug

Use MiniMax M3.1 Flash to trace a reported failure through the relevant code, propose a focused patch, and check it against the reproduction steps.

### Implement a feature from acceptance criteria

Give MiniMax M3.1 Flash a concrete feature specification and ask for an implementation with checks tied to each requirement.

### Plan a code refactor

Ask MiniMax M3.1 Flash to map dependencies, identify behavior that must stay consistent, and divide the refactor into reviewable changes.

### Review code for security issues

Have MiniMax M3.1 Flash inspect application code for vulnerabilities and propose patches. Require a concrete code path and a verification step for each finding.

### Reconcile conflicting documents

Use MiniMax M3.1 Flash to compare long specifications or procedures, locate contradictory requirements, and draft a decision list with supporting passages.

### Build an evidence-based research brief

Ask MiniMax M3.1 Flash to work through supplied material or available research tools, connect relevant findings, and separate supported conclusions from open questions.

### Prepare an operations handoff

Have MiniMax M3.1 Flash gather task status through available tools, reconcile conflicting updates, and produce a handoff with owners, blockers, and next actions.

## Overview

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

## MiniMax M3.1 Flash in other agents

- [Amp](https://spiral.ai/integrations/amp/minimax-m3-1-flash)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/minimax-m3-1-flash)
- [Claude](https://spiral.ai/integrations/claude-desktop/minimax-m3-1-flash)
- [Claude Code](https://spiral.ai/integrations/claude-code/minimax-m3-1-flash)
- [Cline](https://spiral.ai/integrations/cline/minimax-m3-1-flash)
- [Codex](https://spiral.ai/integrations/codex/minimax-m3-1-flash)
- [Cursor](https://spiral.ai/integrations/cursor/minimax-m3-1-flash)
- [Devin](https://spiral.ai/integrations/devin/minimax-m3-1-flash)
- [dots](https://spiral.ai/integrations/dots/minimax-m3-1-flash)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/minimax-m3-1-flash)
- [Gemini](https://spiral.ai/integrations/gemini/minimax-m3-1-flash)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/minimax-m3-1-flash)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/minimax-m3-1-flash)
- [goose](https://spiral.ai/integrations/goose/minimax-m3-1-flash)
- [Grok](https://spiral.ai/integrations/grok/minimax-m3-1-flash)
- [Grok Build](https://spiral.ai/integrations/grok-build/minimax-m3-1-flash)
- [Hermes](https://spiral.ai/integrations/hermes/minimax-m3-1-flash)
- [Manus](https://spiral.ai/integrations/manus/minimax-m3-1-flash)
- [Muse](https://spiral.ai/integrations/muse/minimax-m3-1-flash)
- [Muse Code](https://spiral.ai/integrations/muse-code/minimax-m3-1-flash)
- [n8n](https://spiral.ai/integrations/n8n/minimax-m3-1-flash)
- [Notion](https://spiral.ai/integrations/notion/minimax-m3-1-flash)
- [OpenClaw](https://spiral.ai/integrations/openclaw/minimax-m3-1-flash)
- [opencode](https://spiral.ai/integrations/opencode/minimax-m3-1-flash)
- [Perplexity](https://spiral.ai/integrations/perplexity/minimax-m3-1-flash)
- [Raycast](https://spiral.ai/integrations/raycast/minimax-m3-1-flash)
- [VS Code](https://spiral.ai/integrations/vscode/minimax-m3-1-flash)
- [Windsurf](https://spiral.ai/integrations/windsurf/minimax-m3-1-flash)
- [Zapier](https://spiral.ai/integrations/zapier/minimax-m3-1-flash)

## More Instinct guides

- [MiniMax M3 (batch)](https://spiral.ai/integrations/instinct/minimax-m3-batch)
- [Ministral 3 14B](https://spiral.ai/integrations/instinct/ministral-3-14b)
- [MiniMax M3](https://spiral.ai/integrations/instinct/minimax-m3)
- [Ministral 3 3B](https://spiral.ai/integrations/instinct/ministral-3-3b)
- [MiniMax M2.7](https://spiral.ai/integrations/instinct/minimax-m2-7)
- [Ministral 3 8B](https://spiral.ai/integrations/instinct/ministral-3-8b)

## Questions about MiniMax M3.1 Flash in Instinct

**Can Instinct use MiniMax M3.1 Flash?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run MiniMax M3.1 Flash like any built-in tool.

**How much does MiniMax M3.1 Flash cost in Instinct?**

Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.78 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 M3.1 Flash in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs MiniMax M3.1 Flash on its own OpenRouter account.

**How long does it take to set up MiniMax M3.1 Flash in Instinct?**

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

**Does Instinct wait while MiniMax M3.1 Flash runs?**

MiniMax M3.1 Flash runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is MiniMax M3.1 Flash good at?**

Its documented focus is coding, code security reviews, and work that takes several tool calls. Practical uses include investigating bugs, checking documents for contradictions, and carrying a task through several steps.

**How much context can MiniMax M3.1 Flash handle?**

MiniMax documents a context window of up to 1 million tokens. That is useful for reviewing long documents or substantial code context, but it is separate from the maximum answer length.

**How long can an answer be?**

MiniMax documents a maximum generation limit of 524,288 tokens and recommends 131,072 tokens. Thinking also consumes the output budget, so those figures do not mean an equally long final answer.

**Can MiniMax M3.1 Flash answer without thinking?**

Thinking cannot be disabled. Use a lower thinking depth for straightforward work and reserve deeper thinking for tasks that need more investigation.

**What limitations matter during long tasks?**

Deeper thinking produces more tokens and increases latency. An output budget that is too small can be consumed by thinking before a final answer appears.

