Llama Guard
Content moderation models for safeguarding AI system interactions
- Also known as
- llama-guard
What is Llama Guard?
Open-source moderation models that detect and help prevent harmful content in AI language model inputs and outputs, with capabilities including prompt injection and jailbreak attack detection.
Llama Guard pricing
We don't have Llama Guard's full plan breakdown yet (its pricing page resisted automated reading). Here's what we could confirm. Always check live pricing for exact numbers.
Free and open source under MIT license
What Llama Guard does
The capabilities that matter for ai guardrails, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Architecture model
- Open source python library
- Prompt injection and jailbreak blocking
- ✓
- Inbound pii and credit card masking redaction
- ✗
- Outbound toxicity and competitor mention blocking
- ✓
- Hallucination and topical off brand drift detection
- ✗
- Sub 50ms latency guarantees for proxy routing
- ✗
- Custom regex and deterministic denylist rulesets
- ✗
- Streaming token interception and chunked eval
- ✗
- Rag retrieval chunk poisoning defense
- ✗
- Zero data retention and prompt privacy guarantees
- ✓
- SOC2 type ii
- ✗
- ISO 27001
- ✗
- Pricing model
- Free open source
Platform & deployment
Independently observed- CLI
- Self-hosted
Security & compliance
Known vulnerabilities: 0 (0 in the last 12 months) sourcea count reflects scale & disclosure, not quality
Llama Guard FAQ
Common questions about Llama Guard, answered from independent, dated evidence.
What is Llama Guard?
A suite of input/output moderation models and security evaluation benchmarks designed to help developers build safer generative AI applications. Includes tools to detect prompt injection, jailbreaking attempts, and other violating content. It is indexed under AI Guardrails.
Source: https://github.com/pricing
Is Llama Guard free to use?
Llama Guard is open source, so it can be self-hosted and used at no licence cost. Pricing changes often, so verify at source before relying on it.
Source: https://github.com/pricing
What platforms does Llama Guard support?
Llama Guard supports a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.
Source: https://github.com/pricing
Can Llama Guard be self-hosted?
Yes. Llama Guard can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.
Source: https://github.com/pricing
Llama Guard alternatives
Other ai guardrails we track, ranked by the same independent score.
- Enkrypt AIEnterprise AI governance and security through real-time policy enforcementmedium · 53%
- Arthur ShieldA monitoring and governance platform for AI and machine learning applicationsmedium · 54%
- HiddenLayerA comprehensive security platform purpose-built for AI systems and applicationslow · 29%
- NVIDIA NeMo GuardrailsOpen-source framework for adding safety controls to AI-powered conversation systemslow · 29%
- Lakera GuardAI security platform that detects and blocks threats to large language model applications in real-timemedium · 56%
- RebuffA system that identifies and blocks prompt injection attacks and improves its defenses based on detected attackslow · 24%
Compare Llama Guard
Side by side against other ai guardrails, attribute by attribute, with a source on every value.
The vioscaleAI score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for Llama Guard, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Capabilities | 58 | 0.08 | 4.6 | ✓ |
| Stars | 69 | 0.05 | 3.2 | ✓ |
| Security score | 59 | 0.05 | 3.2 | ✓ |
| Development activity | 19 | 0.14 | 2.6 | ✓ |
| Integrations | 0 | 0.05 | 0.0 | - |
| Dependent projects | 0 | 0.05 | 0.0 | ✓ |
| Release cadence | 0 | 0.08 | 0.0 | - |
| Security posture | 0 | 0.12 | 0.0 | - |
| Package downloads | 0 | 0.04 | 0.0 | - |
| Developer Q&A activity | 0 | 0.14 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Activity
| Attribute | Value | Evidence |
|---|---|---|
| Commits last 30d | 3 | mediumsource · 2026-10-14 · 65% |
Adoption
Content
| Attribute | Value | Evidence |
|---|---|---|
| Faq | 4 items | mediumsource · 2026-09-10 · 60% |
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Iso 27001: No · Soc2 type ii: No · Pricing model: free_open_source · Architecture model: open_source_python_library · Rag retrieval chunk poisoning defense: No · Prompt injection and jailbreak blocking: Yes | mediumsource · 2026-10-14 · 60% |
Language
| Attribute | Value | Evidence |
|---|---|---|
| Primary | Python | highsource · 2026-10-14 · 90% |
Pricing
Security
| Attribute | Value | Evidence |
|---|---|---|
| Scorecard | 5.9 | highsource · 2026-10-14 · 90% |
| Vulnerabilities | Count: 0 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=codeshield&per_page=100 · Last 12m: 0 | highsource · 2026-10-14 · 90% |
| Trust center | https://github.com/security | mediumsource · 2026-10-14 · 60% |
Is Llama Guard the right choice for you?
Tell us the job, the constraints and what you weigh most, and we will rank Llama Guard against the rest of the ai guardrails we index, using the same dated evidence weighted your way.
Free to run, no account needed to start. How the evaluation works
Is this your product?
This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves Llama Guard up or down: nobody can buy rank here, including you.
Take the badge
Live, always current, and free to use on your own site. It shows Llama Guard's independent score and links back to this profile.
<a href="https://www.vioscale.ai/software/llama-guard" target="_blank" rel="noopener">
<img src="https://www.vioscale.ai/badge/software/llama-guard.svg" alt="Llama Guard, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>Markdown, for a README →
[](https://www.vioscale.ai/software/llama-guard)Claim the profile
Verify you control the domain, then point us at the pages that state the facts about Llama Guard and add your own description and media. Free, and it does not change the score.
- Correct anything wrong, with evidence
- Point our crawler at the pages that matter
- Write your own description and add media
Not the owner? How vendor profiles work