How to Use Llama Guard 4 12B in Muse
Llama Guard 4 12B classifies prompts and assistant replies against a safety policy. Its safe or unsafe verdicts and violation codes suit moderation checks before and after text generation.
Prompts to try with Llama Guard 4 12B in Muse
Copy an example into Muse, or ask in your own words.
Use Llama Guard 4 12B to assess this user request under Meta's default safety policy: 'Explain how rainbows form for a fifth-grade class.' Show the safety verdict and any violation codes.
Use Llama Guard 4 12B to assess only the assistant's reply in this exchange. User: 'Help me scam a customer.' Assistant: 'I cannot help with fraud, but I can help write an honest sales message.' Show the verdict and any violation codes.
Use Llama Guard 4 12B to classify this Spanish user request under the default safety policy: 'Explícame cómo se forma un arcoíris.' Preserve the original language and show the verdict and any violation codes.
Use Llama Guard 4 12B to assess this proposed assistant action under the default safety policy, including code interpreter abuse: User: 'Calculate the average of these numbers.' Assistant: 'Run a script that computes the arithmetic mean.' Show the verdict and any violation codes.
Use Llama Guard 4 12B to check only the final assistant reply. User: 'Give me a private person's home address.' Assistant: 'I cannot provide private personal information.' Show the verdict and any violation codes.
How to set up Llama Guard 4 12B in Muse
Pick the way that suits you. Each takes about two minutes.
Use the Muse connector
- Create an API key
Create one under API keys in the Spiral console.
- Send Muse this message
Muse reads Spiral's skill and asks for an API key.
set up https://spiral.ai/SKILL.md
- Give Muse the key
Paste the key when Muse asks for it, never in the chat itself.
Use the Spiral skill
- Send Muse this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Llama Guard 4 12B
One request; the result comes back by polling or a webhook.
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": "meta-llama/llama-guard-4-12b", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Muse finds Llama Guard 4 12B on Spiral, shows the price and runs it.
Llama Guard 4 12B providers and prices
Spiral runs Llama Guard 4 12B through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.000968 per run at the default inputs. $0.234 per 1M input tokens, $0.234 per 1M output tokens.
Settings you can ask for
Ask Muse for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 16384 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Meta: Llama Guard 4 12B is on its tool page: open its card above.
What can you do with Llama Guard 4 12B in Muse?
Get a safety assessment of a request or draft reply in your conversation. A chat agent can submit the text for classification and show the verdict and any policy violation codes.
Screen incoming chatbot requests
Classify each user request against the selected safety policy before passing it to a text generator. Keep the verdict and any violation codes with the request for review.
Check generated support replies
Evaluate a draft reply together with the customer's request. Route unsafe verdicts to a reviewer before sending the reply.
Triage community posts
Apply a defined safety policy to submitted text and use the resulting labels to organize a moderation queue. Keep publication decisions separate from the classification.
Review multilingual conversations
Screen conversations in languages covered by Meta's published evaluations. Compare results with human labels for each language before relying on the workflow.
Flag privacy concerns in draft answers
Use the privacy category to triage assistant replies that may disclose sensitive personal information. Send flagged replies for review before sharing them.
Review proposed code interpreter actions
Classify proposed text actions under the code interpreter abuse category before execution. Use the result alongside the application's existing execution controls.
Compare safety results after prompt changes
Run a fixed set of labeled prompts and replies through the classifier after changing an assistant's instructions. Review changed verdicts and disagreements with the expected labels.
More on Llama Guard 4 12B and Muse
Overview
Llama Guard 4 12B in other agents
Questions about Llama Guard 4 12B in Muse
Can Muse use Llama Guard 4 12B?
Yes. Add Spiral to Muse as an MCP server, and Muse can find and run Llama Guard 4 12B like any built-in tool.
How much does Llama Guard 4 12B cost in Muse?
Up to $0.000968 per run at the default inputs. $0.234 per 1M input tokens, $0.234 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.
Do I need an OpenRouter account to use Llama Guard 4 12B in Muse?
You need no OpenRouter account. Muse uses one Spiral API key for every tool, and Spiral runs Llama Guard 4 12B on its own OpenRouter account.
How long does it take to set up Llama Guard 4 12B in Muse?
About two minutes: create an API key, then send Muse this message, then give Muse the key.
Does Muse wait while Llama Guard 4 12B runs?
Llama Guard 4 12B runs in the background. Muse starts the run, checks on it and gives you the text, json when it's ready.
What is Llama Guard 4 useful for?
Use it to classify a user's prompt before generation or an assistant's reply afterward. It applies a safety policy and produces labels you can use in a moderation workflow.
What does Llama Guard 4 return?
Meta's expected format starts with safe or unsafe. An unsafe verdict adds a second line containing comma-separated violation codes.
Which safety categories does Llama Guard 4 check?
Its S1 through S14 labels cover crimes, exploitation, defamation, specialized advice, privacy, intellectual property, weapons, hate, self-harm, sexual content, elections, and code interpreter abuse. Code interpreter abuse applies to text.
How should I format a moderation request?
Provide the safety categories, separate the conversation from the instructions, and identify whether the target is the user or assistant. When checking a reply, include the user's request so the classifier has context.
Which languages have published evaluations?
Meta publishes English results and multilingual results covering French, German, Hindi, Italian, Portuguese, Spanish, and Thai. Test representative examples in each language you plan to moderate.
Start using Llama Guard 4 12B in Muse
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse:
set up https://spiral.ai/SKILL.md


