[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [GPT-oss Safeguard 20B](https://spiral.ai/integrations/claude-code/gpt-oss-safeguard-20b)

# How to Use GPT-oss Safeguard 20B in Claude Code

GPT-oss Safeguard 20B classifies text against safety rules you supply and can explain each decision. Compared with GPT-oss Safeguard 120B, it targets lower latency and specialized moderation tasks.

|  |  |
| --- | --- |
| Model | GPT-oss Safeguard 20B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001602 per run at the default inputs. $0.0975 per 1M input tokens, $0.39 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-oss Safeguard 20B in Claude Code

- Use GPT-oss Safeguard 20B to classify the moderation fixtures in this project under its existing community policy. Report each expected label, predicted label, and mismatch.
- Use GPT-oss Safeguard 20B to review the saved assistant responses in our test fixtures against the project's safety policy. Report the response ID and applicable rule for each violation.
- Use GPT-oss Safeguard 20B to label our incoming-message fixtures under the current abuse policy. Preserve fixture IDs and compare the results with the existing human labels.
- Use GPT-oss Safeguard 20B to classify the same moderation fixtures at low, medium, and high reasoning effort. Compare errors against the human labels and report measured response times.
- Use GPT-oss Safeguard 20B to review our conversation fixtures under the written harassment policy. Judge each complete conversation and list any decisions that differ from the single-message labels.

## How to set up GPT-oss Safeguard 20B in Claude Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude Code 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 GPT-oss Safeguard 20B**: 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": "openai/gpt-oss-safeguard-20b",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Claude Code finds GPT-oss Safeguard 20B on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## GPT-oss Safeguard 20B tools and prices

- [OpenAI: gpt-oss-safeguard-20b](https://spiral.ai/tools/openrouter/openai/gpt-oss-safeguard-20b) (OpenRouter): Up to $0.001602 per run at the default inputs. $0.0975 per 1M input tokens, $0.39 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 65536 | — | The most output tokens to generate. |

## What can you do with GPT-oss Safeguard 20B in Claude Code?

Check your application's text safety decisions against its written rules. Use project policies and labeled fixtures to compare results before changing moderation behavior.

### Community post review

Classify forum posts against written rules for threats, harassment, or prohibited promotion.

### Assistant response checks

Review generated responses against your safety policy before deciding whether to show them.

### Incoming message screening

Label user requests under your product's safety rules before passing them to another assistant.

### Conversation review

Evaluate complete text conversations when a single message does not provide enough context for a policy decision.

### Review authenticity screening

Flag product reviews that match your written criteria for suspected fabrication or undisclosed incentives.

### Stored content labeling

Apply a defined safety taxonomy to archived text for a Trust and Safety review project.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## GPT-oss Safeguard 20B in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-oss-safeguard-20b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-oss-safeguard-20b)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-oss-safeguard-20b)
- [Cline](https://spiral.ai/integrations/cline/gpt-oss-safeguard-20b)
- [Codex](https://spiral.ai/integrations/codex/gpt-oss-safeguard-20b)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-oss-safeguard-20b)
- [Devin](https://spiral.ai/integrations/devin/gpt-oss-safeguard-20b)
- [dots](https://spiral.ai/integrations/dots/gpt-oss-safeguard-20b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-oss-safeguard-20b)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-oss-safeguard-20b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-oss-safeguard-20b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-oss-safeguard-20b)
- [goose](https://spiral.ai/integrations/goose/gpt-oss-safeguard-20b)
- [Grok](https://spiral.ai/integrations/grok/gpt-oss-safeguard-20b)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-oss-safeguard-20b)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-oss-safeguard-20b)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-oss-safeguard-20b)
- [Manus](https://spiral.ai/integrations/manus/gpt-oss-safeguard-20b)
- [Muse](https://spiral.ai/integrations/muse/gpt-oss-safeguard-20b)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-oss-safeguard-20b)
- [n8n](https://spiral.ai/integrations/n8n/gpt-oss-safeguard-20b)
- [Notion](https://spiral.ai/integrations/notion/gpt-oss-safeguard-20b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-oss-safeguard-20b)
- [opencode](https://spiral.ai/integrations/opencode/gpt-oss-safeguard-20b)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-oss-safeguard-20b)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-oss-safeguard-20b)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-oss-safeguard-20b)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-oss-safeguard-20b)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-oss-safeguard-20b)

## More Claude Code guides

- [GPT-6.2 Sol Pro](https://spiral.ai/integrations/claude-code/gpt-6-2-sol-pro)
- [GPT-oss-120B](https://spiral.ai/integrations/claude-code/gpt-oss-120b)
- [GPT-6.2 Sol](https://spiral.ai/integrations/claude-code/gpt-6-2-sol)
- [Gemini 3 Flash Preview](https://spiral.ai/integrations/claude-code/gemini-3-flash-preview)
- [GPT-6.2 Astra Pro](https://spiral.ai/integrations/claude-code/gpt-6-2-astra-pro)
- [Gemini 3.1 Flash-Lite](https://spiral.ai/integrations/claude-code/gemini-3-1-flash-lite)

## Questions about GPT-oss Safeguard 20B in Claude Code

**Can Claude Code use GPT-oss Safeguard 20B?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run GPT-oss Safeguard 20B like any built-in tool.

**How much does GPT-oss Safeguard 20B cost in Claude Code?**

Up to $0.001602 per run at the default inputs. $0.0975 per 1M input tokens, $0.39 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

**Do I need an OpenRouter account to use GPT-oss Safeguard 20B in Claude Code?**

No. Spiral runs GPT-oss Safeguard 20B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up GPT-oss Safeguard 20B in Claude Code?**

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

**Does Claude Code wait while GPT-oss Safeguard 20B runs?**

GPT-oss Safeguard 20B runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-oss Safeguard good at?**

It labels text according to safety policies you provide. Use it to review community posts, check assistant responses, or classify conversations under your own rules.

**Can GPT-oss Safeguard replace a general chat or coding model?**

OpenAI recommends it for safety classification. For general conversation or software development, OpenAI recommends GPT-oss instead.

**How should I write a moderation policy?**

Separate instructions, definitions, decision criteria, and examples. Define what is allowed as carefully as what violates the rules.

**Which reasoning setting should I test?**

Test low, medium, and high effort on the same labeled examples. Choose based on classification results and the response time your task allows.

**What are its main limitations?**

It handles text, so image or audio moderation requires a separate model. A dedicated classifier trained on a large labeled dataset can also outperform it on complex risks.

