[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [GPT-5 Mini](https://spiral.ai/integrations/openclaw/gpt-5-mini)

# How to Use GPT-5 Mini in OpenClaw

GPT-5 Mini suits focused coding tasks, text extraction, and summaries with clear requirements. It responds faster than GPT-5 and works best when you specify exactly what a successful answer includes.

|  |  |
| --- | --- |
| Model | GPT-5 Mini |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.010662 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $2.60 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5 Mini in OpenClaw

- Each morning, use GPT-5 Mini to summarize the updates supplied for that run. Report new decisions, changed deadlines, and unresolved blockers in under 300 words. Include source identifiers and omit repeated information.
- Every hour, use GPT-5 Mini to classify newly supplied support messages as billing, access, product question, or unclear. Include a supporting excerpt for each classification and flag messages that fit multiple categories.
- At the end of each day, use GPT-5 Mini to extract commitments from the supplied meeting transcripts. Record the action, owner, deadline, and supporting sentence. Write unknown for missing details.
- Each week, use GPT-5 Mini with high reasoning effort to compare the supplied policy updates with the previous policy text. List changed obligations and conflicting passages. Support each finding with excerpts from both versions.
- Each afternoon, use GPT-5 Mini to draft replies for the supplied unanswered customer questions using the current policy text. Keep each draft under 120 words and flag questions the policy cannot resolve.

## How to set up GPT-5 Mini in OpenClaw

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

### Use the Spiral skill

1. **Send OpenClaw 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. **Add the server**: On the machine that runs OpenClaw's Gateway:

```bash
openclaw mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --transport streamable-http \
  --auth oauth
```

2. **Sign in**: In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

```bash
openclaw mcp login spiral
```

3. **Reload and check**: A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

```bash
openclaw mcp reload
openclaw mcp doctor spiral --probe
```

### 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 GPT-5 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": "openai",
    "model": "openai/gpt-5-mini",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds GPT-5 Mini on Spiral, shows the price and runs it.

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

## GPT-5 Mini tools and prices

- [GPT-5 Mini](https://spiral.ai/tools/openai/openai/gpt-5-mini) (OpenAI): Up to $0.010662 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $2.60 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 16 to 128000 | — | The most output tokens to generate. |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with GPT-5 Mini in OpenClaw?

Turn recurring batches of messages and updates into consistent review queues with GPT-5 Mini. Define the classification rules, evidence requirements, and conditions for flagging an item.

### Extract order details

Turn order messages into consistent records containing order numbers, requested changes, and dates. Require a missing value when the message does not provide a detail.

### Sort support requests

Assign incoming messages to clearly defined categories such as billing, access, and product questions. Include a short supporting excerpt for each decision.

### Summarize meeting decisions

Extract decisions, owners, deadlines, and unresolved questions from a transcript. Keep proposed actions separate from agreed commitments.

### Draft answers from supplied policies

Prepare support reply drafts using the customer's message and current policy text. Flag questions the policy does not answer.

### Fix a specific software bug

Investigate a reproducible failure, propose a focused patch, and check it against the expected behavior. Keep the task scoped to the reported issue.

### Write regression tests

Turn a bug report and acceptance criteria into tests for the reported failure and relevant edge cases. Review the tests against the intended behavior.

### Prepare a daily change digest

Compare supplied updates with the previous digest and report changes, unresolved items, and supporting excerpts. Use explicit rules to exclude repeated information.

## Overview

- [OpenAI](https://spiral.ai/providers/openai)
- [All OpenClaw guides](https://spiral.ai/integrations/openclaw)

## GPT-5 Mini in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-5-mini)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-5-mini)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-5-mini)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-5-mini)
- [Cline](https://spiral.ai/integrations/cline/gpt-5-mini)
- [Codex](https://spiral.ai/integrations/codex/gpt-5-mini)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-5-mini)
- [Devin](https://spiral.ai/integrations/devin/gpt-5-mini)
- [dots](https://spiral.ai/integrations/dots/gpt-5-mini)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-5-mini)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-5-mini)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-5-mini)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-5-mini)
- [goose](https://spiral.ai/integrations/goose/gpt-5-mini)
- [Grok](https://spiral.ai/integrations/grok/gpt-5-mini)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-5-mini)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-5-mini)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-5-mini)
- [Manus](https://spiral.ai/integrations/manus/gpt-5-mini)
- [Muse](https://spiral.ai/integrations/muse/gpt-5-mini)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-5-mini)
- [n8n](https://spiral.ai/integrations/n8n/gpt-5-mini)
- [Notion](https://spiral.ai/integrations/notion/gpt-5-mini)
- [opencode](https://spiral.ai/integrations/opencode/gpt-5-mini)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-5-mini)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-5-mini)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-5-mini)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-5-mini)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-5-mini)

## More OpenClaw guides

- [GPT-5](https://spiral.ai/integrations/openclaw/gpt-5)
- [GPT-5 Nano](https://spiral.ai/integrations/openclaw/gpt-5-nano)
- [GPT-4o mini (2024-07-18)](https://spiral.ai/integrations/openclaw/gpt-4o-mini-2024-07-18)
- [GPT-5 Pro](https://spiral.ai/integrations/openclaw/gpt-5-pro)
- [GPT-4o mini](https://spiral.ai/integrations/openclaw/gpt-4o-mini)
- [GPT-5.1](https://spiral.ai/integrations/openclaw/gpt-5-1)

## Questions about GPT-5 Mini in OpenClaw

**Can OpenClaw use GPT-5 Mini?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run GPT-5 Mini like any built-in tool.

**How much does GPT-5 Mini cost in OpenClaw?**

Up to $0.010662 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $2.60 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

**Do I need an OpenAI account to use GPT-5 Mini in OpenClaw?**

No. Spiral runs GPT-5 Mini on its own OpenAI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up GPT-5 Mini in OpenClaw?**

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

**Does OpenClaw wait while GPT-5 Mini runs?**

GPT-5 Mini runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-5 Mini best suited for?**

Start with well-defined tasks: extract details from text, summarize a discussion against a checklist, or fix a specific coding issue. Give it the source material and a clear description of the result you need.

**How much text can GPT-5 Mini handle?**

Its context window is 400,000 tokens, and its maximum output is 128,000 tokens. Reasoning also consumes the generation budget, so that output limit does not mean 128,000 tokens of visible text.

**Does GPT-5 Mini know about recent events?**

Its built-in knowledge cutoff is May 31, 2024. Supply recent source material when dates, policies, or other changing details matter.

**How should I prompt GPT-5 Mini?**

State the task, separate the source text from your instructions, and specify the required format and length. Remove conflicting requirements and give a clear rule for missing information.

**When should I give GPT-5 Mini more reasoning effort?**

Test higher effort when a task involves difficult debugging or several dependent decisions. Lower effort is worth testing for straightforward work where less exploration is useful.

