[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Inkling 2 Mini](https://spiral.ai/integrations/instinct/inkling-2-mini)

# How to Use Inkling 2 Mini in Instinct

Inkling 2 Mini is a compact reasoning model for coding, research with tools, and document questions. Its strengths are multistep agent tasks; long conversations and instructions with many constraints need closer review.

|  |  |
| --- | --- |
| Model | Inkling 2 Mini |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.034084 per run at the default inputs. $0.13 per 1M input tokens, $0.52 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Inkling 2 Mini in Instinct

- Use Inkling 2 Mini each morning to check official release notes for Python, Node.js, and PostgreSQL. Compare them with the previous run's summary and report new releases with dates and source links.
- Use Inkling 2 Mini each weekday to review newly received support reports. Group reports by observed symptom, cite report IDs, and suggest a reproducible check for each cluster.
- Use Inkling 2 Mini every Monday to check official browser release notes for changes to CSS anchor positioning. Compare with the previous summary and report only new support changes or documented limitations.
- Use Inkling 2 Mini with medium reasoning effort each evening to review today's failed job results. Group matching failures, distinguish observed errors from hypotheses, and produce a short investigation queue.
- Use Inkling 2 Mini each Friday to research changes in W3C guidance on accessible forms. Use primary sources, compare against the previous run's summary, and return new findings or state that no relevant changes were found.

## How to set up Inkling 2 Mini 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 Inkling 2 Mini**: 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": "thinkingmachines/inkling-2-mini",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Inkling 2 Mini on Spiral, shows the price and runs it.

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

## Inkling 2 Mini tools and prices

- [Thinking Machines: Inkling 2 Mini](https://spiral.ai/tools/openrouter/thinkingmachines/inkling-2-mini) (OpenRouter): Up to $0.034084 per run at the default inputs. $0.13 per 1M input tokens, $0.52 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 Inkling 2 Mini in Instinct?

Inkling 2 Mini can turn recurring searches and tool results into change reports and investigation queues. Give each run a narrow question and the previous summary so the output focuses on what changed.

### Fix a reproducible bug

Give Inkling 2 Mini the failing behavior, relevant code, and expected result. Ask for a focused patch and a regression test that demonstrates the fix.

### Plan and carry out a code migration

Ask Inkling 2 Mini to identify affected call sites, update one component at a time, and check behavior against the migration requirements.

### Find missing test coverage

Have Inkling 2 Mini compare an implementation with its existing tests, identify uncovered behavior, and propose cases with explicit expected results.

### Research a narrow question

Use Inkling 2 Mini with search tools to investigate a specific claim. Request primary sources, supporting passages, and a clear account of unresolved evidence.

### Answer questions across long documents

Provide labeled source text and ask Inkling 2 Mini to locate relevant passages, reconcile conflicting statements, and cite the evidence behind its answer.

### Prepare a recurring change brief

Have Inkling 2 Mini compare newly retrieved announcements with the previous run's summary. Request only substantive changes, source links, and open questions.

### Turn support reports into investigation steps

Give Inkling 2 Mini a set of reports and ask it to separate observed symptoms from suspected causes, group related issues, and propose reproducible checks.

## Overview

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

## Inkling 2 Mini in other agents

- [Amp](https://spiral.ai/integrations/amp/inkling-2-mini)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/inkling-2-mini)
- [Claude](https://spiral.ai/integrations/claude-desktop/inkling-2-mini)
- [Claude Code](https://spiral.ai/integrations/claude-code/inkling-2-mini)
- [Cline](https://spiral.ai/integrations/cline/inkling-2-mini)
- [Codex](https://spiral.ai/integrations/codex/inkling-2-mini)
- [Cursor](https://spiral.ai/integrations/cursor/inkling-2-mini)
- [Devin](https://spiral.ai/integrations/devin/inkling-2-mini)
- [dots](https://spiral.ai/integrations/dots/inkling-2-mini)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/inkling-2-mini)
- [Gemini](https://spiral.ai/integrations/gemini/inkling-2-mini)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/inkling-2-mini)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/inkling-2-mini)
- [goose](https://spiral.ai/integrations/goose/inkling-2-mini)
- [Grok](https://spiral.ai/integrations/grok/inkling-2-mini)
- [Grok Build](https://spiral.ai/integrations/grok-build/inkling-2-mini)
- [Hermes](https://spiral.ai/integrations/hermes/inkling-2-mini)
- [Manus](https://spiral.ai/integrations/manus/inkling-2-mini)
- [Muse](https://spiral.ai/integrations/muse/inkling-2-mini)
- [Muse Code](https://spiral.ai/integrations/muse-code/inkling-2-mini)
- [n8n](https://spiral.ai/integrations/n8n/inkling-2-mini)
- [Notion](https://spiral.ai/integrations/notion/inkling-2-mini)
- [OpenClaw](https://spiral.ai/integrations/openclaw/inkling-2-mini)
- [opencode](https://spiral.ai/integrations/opencode/inkling-2-mini)
- [Perplexity](https://spiral.ai/integrations/perplexity/inkling-2-mini)
- [Raycast](https://spiral.ai/integrations/raycast/inkling-2-mini)
- [VS Code](https://spiral.ai/integrations/vscode/inkling-2-mini)
- [Windsurf](https://spiral.ai/integrations/windsurf/inkling-2-mini)
- [Zapier](https://spiral.ai/integrations/zapier/inkling-2-mini)

## More Instinct guides

- [Inkling](https://spiral.ai/integrations/instinct/inkling)
- [Inkling 2 Small](https://spiral.ai/integrations/instinct/inkling-2-small)
- [Hy4 Preview](https://spiral.ai/integrations/instinct/hy4-preview)
- [Inkling Small](https://spiral.ai/integrations/instinct/inkling-small)
- [Hy4 Flash](https://spiral.ai/integrations/instinct/hy4-flash)
- [Inkling Small (batch)](https://spiral.ai/integrations/instinct/inkling-small-batch)

## Questions about Inkling 2 Mini in Instinct

**Can Instinct use Inkling 2 Mini?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Inkling 2 Mini like any built-in tool.

**How much does Inkling 2 Mini cost in Instinct?**

Up to $0.034084 per run at the default inputs. $0.13 per 1M input tokens, $0.52 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 Inkling 2 Mini in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Inkling 2 Mini on its own OpenRouter account.

**How long does it take to set up Inkling 2 Mini in Instinct?**

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

**Does Instinct wait while Inkling 2 Mini runs?**

Inkling 2 Mini runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is Inkling 2 Mini best suited for?**

Coding tasks that require several steps and research that uses search or other tools are good starting points. Give it a concrete goal and a way to check the result, such as a failing test or a source citation.

**Where does Inkling 2 Mini need closer review?**

Thinking Machines flags long conversations and instructions with many constraints as weaker areas. Keep the current task self-contained, list the essential requirements, and check the result against them.

**How much context can Inkling 2 Mini handle?**

The published model supports up to one million tokens of context. For document questions, label the sources and ask for supporting passages so you can check each conclusion.

**Can Inkling 2 Mini understand or generate images?**

It accepts images alongside text and returns text. For optimal image performance, Thinking Machines recommends keeping each image dimension between 40 and 4,096 pixels.

**Does Inkling 2 Mini support languages besides English?**

Yes. Its model card lists English and general multilingual support; specify the output language and review terminology for your audience.

