[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Inkling 2 Small](https://spiral.ai/integrations/gemini-cli/inkling-2-small)

# How to Use Inkling 2 Small in Gemini CLI

Inkling 2 Small suits coding tasks, image analysis, and work that takes several tool calls to finish. Compared with Inkling, its gains are especially pronounced on extended autonomous tasks.

|  |  |
| --- | --- |
| Model | Inkling 2 Small |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.00534 per run at the default inputs. $0.39 per 1M input tokens, $1.30 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Inkling 2 Small in Gemini CLI

- Use Inkling 2 Small to investigate the failing tests in this project. Trace the cause, make the smallest justified repair, and run the relevant tests. End with the cause, changed files, and test results.
- Use Inkling 2 Small to inspect this project's sign-in flow and add a regression test for an expired session. Explain the expected behavior before changing code, then verify it.
- Use Inkling 2 Small to compare the attached screenshot with this project's checkout page. Identify three visible mismatches, fix them, and inspect a fresh screenshot before reporting.
- Use Inkling 2 Small to trace how this project validates incoming requests. Find duplicated validation rules, propose a bounded refactor, and verify that accepted and rejected inputs stay consistent.
- Use Inkling 2 Small to compare the implementation with the requirements in this repository. List unmet requirements with file references, implement one clearly scoped fix, and verify it.

## How to set up Inkling 2 Small in Gemini CLI

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

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI 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 Inkling 2 Small**: 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-small",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Inkling 2 Small tools and prices

- [Thinking Machines: Inkling 2 Small](https://spiral.ai/tools/openrouter/thinkingmachines/inkling-2-small) (OpenRouter): Up to $0.00534 per run at the default inputs. $0.39 per 1M input tokens, $1.30 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 Small in Gemini CLI?

Turn repository context into code changes that include verification. Give Inkling 2 Small a bounded task, relevant project files, and clear acceptance criteria.

### Investigate a failing test

Ask Inkling 2 Small to trace a failure through the relevant code, propose a repair, and verify the result with a focused test.

### Implement a scoped feature

Give Inkling 2 Small acceptance criteria and ask it to carry the change through implementation and verification.

### Turn screenshots into bug reports

Have Inkling 2 Small identify visible interface problems and turn each one into a reproduction checklist with expected behavior.

### Extract text from scanned material

Ask Inkling 2 Small to transcribe an image, preserve headings and table relationships, and mark anything it cannot read.

### Explain a chart

Use Inkling 2 Small to read labels, compare plotted values, and distinguish visible trends from explanations the chart cannot establish.

### Compare lengthy source material

Ask Inkling 2 Small to reconcile requirements or reports, identify contradictions, and attach a source passage to each finding.

### Prepare a research brief

Give Inkling 2 Small a focused question and available search tools, then request an evidence table and a short account of unresolved questions.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Inkling 2 Small in other agents

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

## More Gemini CLI guides

- [Inkling 2 Mini](https://spiral.ai/integrations/gemini-cli/inkling-2-mini)
- [Inkling Small](https://spiral.ai/integrations/gemini-cli/inkling-small)
- [Inkling](https://spiral.ai/integrations/gemini-cli/inkling)
- [Inkling Small (batch)](https://spiral.ai/integrations/gemini-cli/inkling-small-batch)
- [Hy4 Preview](https://spiral.ai/integrations/gemini-cli/hy4-preview)
- [Kimi K2 0711](https://spiral.ai/integrations/gemini-cli/kimi-k2-0711)

## Questions about Inkling 2 Small in Gemini CLI

**Can Gemini CLI use Inkling 2 Small?**

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

**How much does Inkling 2 Small cost in Gemini CLI?**

Up to $0.00534 per run at the default inputs. $0.39 per 1M input tokens, $1.30 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need an OpenRouter account to use Inkling 2 Small in Gemini CLI?**

No. Spiral runs Inkling 2 Small on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Inkling 2 Small in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while Inkling 2 Small runs?**

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

**What is Inkling 2 Small good at?**

Coding, visual analysis, reasoning, and knowledge work are its main strengths. Thinking Machines reports especially pronounced improvements over its first generation on tasks that require sustained autonomous work.

**Can Inkling 2 Small read screenshots and charts?**

Yes. It supports reading text in images, locating visual elements, interpreting infographics, and reasoning about what an image shows.

**Does Inkling 2 Small accept audio?**

No. Use text or images as the source material.

**How much context does Inkling 2 Small support?**

The model supports up to one million tokens of context. That is a context capacity, not a promise of a million-token answer.

**Which languages does Inkling 2 Small support?**

Thinking Machines describes support for English, other natural languages, and multiple coding languages. Its model card does not provide an exhaustive language list.

