[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Inkling Small (batch)](https://spiral.ai/integrations/chatgpt/inkling-small-batch)

# How to Use Inkling Small (batch) in ChatGPT

Inkling Small suits coding, rubric-based grading, and synthetic training examples. In the maker's evaluations, it beats Inkling on reasoning and agentic coding, while Inkling retains an advantage in factuality.

|  |  |
| --- | --- |
| Model | Inkling Small (batch) |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.005129 per run at the default inputs. $0.468 per 1M input tokens, $1.248 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Inkling Small (batch) in ChatGPT

- Use Inkling Small to answer my question using only the passages I provide. Cite the supporting passage for each conclusion and say when the evidence is insufficient.
- Use Inkling Small to grade the answers in this conversation against my rubric. Explain each deduction and separate factual errors from missing detail.
- Use Inkling Small to compare the two policies I provide. List changed obligations, exceptions, and unresolved contradictions, with supporting quotations.
- Use Inkling Small to draft a Spanish support reply from the approved guidance I provide. Preserve product names and glossary terms, and flag wording that needs a language review.
- Use Inkling Small with more thinking effort to examine my proposed solution. Check each step against the stated requirements and return the first unsupported assumption plus a corrected approach.

## How to set up Inkling Small (batch) in ChatGPT

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

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT 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 Small (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": "thinkingmachines/inkling-small:batch",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Inkling Small (batch) on Spiral, shows the price and runs it.

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

## Inkling Small (batch) tools and prices

- [Thinking Machines: Inkling Small (batch)](https://spiral.ai/tools/openrouter/thinkingmachines/inkling-small%3Abatch) (OpenRouter): Up to $0.005129 per run at the default inputs. $0.468 per 1M input tokens, $1.248 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 Small (batch) in ChatGPT?

Use Inkling Small to work through questions using supplied evidence and explicit criteria. Bring documentation excerpts, a grading rubric, or approved support guidance, and ask for a concise result you can check.

### Repair a reproducible bug

Ask Inkling Small to trace a failing test, propose a focused code change, and check the result against the original failure.

### Grade answers against a rubric

Give Inkling Small the reference answer and scoring rules. Request a score, supporting evidence, and a reason for each deduction.

### Draft synthetic training examples

Use Inkling Small to draft labeled examples from a written policy, including ambiguous cases for human review.

### Answer questions from retrieved passages

Provide Inkling Small with relevant documentation excerpts. Require passage citations and an explicit statement when the evidence does not answer the question.

### Compare a specification with an implementation

Have Inkling Small map written requirements to code behavior and identify missing cases, with references to the supplied evidence.

### Draft localized support replies

Give Inkling Small approved support guidance and a terminology glossary. Ask for a reply in the customer's language, then review meaning and terminology.

## Overview

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

## Inkling Small (batch) in other agents

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

## More ChatGPT guides

- [Inkling Small](https://spiral.ai/integrations/chatgpt/inkling-small)
- [Kimi K2 0711](https://spiral.ai/integrations/chatgpt/kimi-k2-0711)
- [Inkling 2 Small](https://spiral.ai/integrations/chatgpt/inkling-2-small)
- [Kimi K2 0905](https://spiral.ai/integrations/chatgpt/kimi-k2-0905)
- [Inkling 2 Mini](https://spiral.ai/integrations/chatgpt/inkling-2-mini)
- [Kimi K2 Thinking](https://spiral.ai/integrations/chatgpt/kimi-k2-thinking)

## Questions about Inkling Small (batch) in ChatGPT

**Can ChatGPT use Inkling Small (batch)?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Inkling Small (batch) like any built-in tool.

**How much does Inkling Small (batch) cost in ChatGPT?**

Up to $0.005129 per run at the default inputs. $0.468 per 1M input tokens, $1.248 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

**Do I need an OpenRouter account to use Inkling Small (batch) in ChatGPT?**

No. Spiral runs Inkling Small (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 Inkling Small (batch) in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while Inkling Small (batch) runs?**

Inkling Small (batch) runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.

**What is Inkling Small good at?**

Coding, reasoning, grading against a rubric, and generating synthetic training examples are supported uses. Give it a concrete task and an explicit standard for a correct answer.

**How does Inkling Small compare with Inkling?**

The maker reports stronger reasoning and agentic coding benchmark results for Inkling Small. Inkling retains an advantage in knowledge coverage and factuality.

**How much context can Inkling Small handle?**

Thinking Machines specifies a context window of up to one million tokens for the model. For document analysis, ask for supporting passages and identify which documents should take priority.

**Does more thinking always improve the answer?**

No. Higher effort generally encourages more reasoning, but the maker says it does not guarantee greater accuracy on every response. Compare results on representative tasks before choosing an effort level.

**Can Inkling Small work in languages besides English?**

Yes, the maker documents general multilingual support. Test the language and terminology you need with real examples before using the results.

