{ "data": { "a": { "slug": "llama-guard", "name": "Llama Guard 4", "vendor": "Meta", "vendorUrl": "https://dev.meta.ai/llama", "kind": "model", "category": "guardrails", "summary": "Llama Guard 4 is Meta's 12-billion-parameter open-weight safety classifier for text and images. It labels a prompt or a model response safe or unsafe against 14 hazard categories, and the owner runs it on a GPU.", "url": "https://www.anchorterminal.com/tools/llama-guard", "markdownUrl": "https://www.anchorterminal.com/tools/llama-guard.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/llama-guard.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/llama-guard.json", "repo": "https://github.com/meta-llama/PurpleLlama", "license": "Llama 4 Community Licence (source-available weights, not an OSI licence), with the Llama 4 acceptable use policy", "transports": [ "http" ], "packages": [], "auth": "none", "authNotes": "Running the model needs no account or key. Getting the weights does. The Hugging Face repository is gated with manual review by Meta and asks for a legal name, date of birth and organisation, and downloads then use a Hugging Face access token. Meta's own download form emails a signed link after the licence is accepted. A vLLM or SGLang server has whatever authentication the owner adds.", "pricing": "free", "pricingNotes": "Free to download and run under the Llama 4 Community Licence, with the owner's GPU as the cost. Meta sells no hosted version that we found. Third parties do, with DeepInfra at $0.18 per 1M tokens and the same price listed on OpenRouter (checked 2026-10-08).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Llama Guard 4 is a model the owner runs, with no payment route (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4423, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://dev.meta.ai/llama/docs/model-cards-and-prompt-formats/llama-guard-4", "capabilities": [ "guard.moderation", "guard.policy", "guard.self-host" ], "tags": [ "model", "open-weights", "self-hosted", "local", "free", "gated", "multimodal", "python", "openai-compatible" ], "lastRelease": "2025-04-29", "graded": true, "anchor": { "graded": true, "score": 49.1, "grade": "D", "agentReady": false, "rank": 614, "ranked": true, "rankOf": 722, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 28, "payments": 45, "reliability": 38, "schema": 52, "security": 53, "transparency": 55 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "A single self-hosted model classifies text and multi-image prompts against 14 MLCommons-aligned hazard categories and answers in a few tokens. The weights have not changed since 29 April 2025, download access needs Meta's manual approval, and the licence withholds the grant from individuals and companies based in the European Union.", "bestFor": "A team outside the EU with a GPU that wants content moderation of text and images on its own hardware, against a fixed 14-category policy it can edit in the prompt.", "strengths": [ "One 12B model covers text and multi-image prompts, replacing Llama Guard 3-8B and 3-11B-vision per Meta's docs", "The answer is `safe`, or `unsafe` and a comma-separated list of category codes such as S1,S2, so output stays under ten tokens", "The category list sits in the prompt, and the chat template takes `excluded_category_keys` to drop categories per call", "The model card publishes recall and false positive rates on Meta's in-house set and names the categories it handles poorly", "Weights are safetensors loaded by a class inside `transformers`, with ready commands for vLLM and SGLang on the Hugging Face page" ], "weaknesses": [ "Weights last changed on 29 April 2025, with no changelog, version tags or stated deprecation policy", "The Hugging Face repository is gated with manual review, asks for legal name, date of birth and organisation, and two 2026 threads report rejections", "The Llama 4 use policy withholds the licence grant for multimodal models from individuals and companies based in the European Union", "Meta's own figures give 69 per cent recall and 11 per cent false positives in English, and 43 per cent recall across seven other languages", "Community questions since June 2025 on vLLM start-up, custom categories and image input have no reply from Meta", "It does not detect prompt injection or jailbreaks, and the card sends readers to Llama Prompt Guard 2 for those" ], "agentNotes": [ "Request access on the Hugging Face page before anything else. Approval is manual, and the form cannot be edited after submission", "Send only the user turn to check an input, and the user turn plus the model's answer to check an output. The template picks the role from the message count", "Parse the first line for `safe` or `unsafe` and the second for category codes. Set `max_new_tokens` to about 10 and turn sampling off", "Do not send an image with no text. Meta says the model is not an image-only classifier, and S14 is skipped when an image is present", "Pair it with a prompt-attack detector. The card says the model can itself be moved by adversarial or injected text" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 49.1 } ], "editorialScores": { "ergonomics": 67, "maintenance": 28, "payments": 45, "reliability": 38, "schema": 52, "security": 53, "transparency": 52 }, "provenanceScore": 58 }, "connect": { "install": "pip install vllm\nvllm serve \"meta-llama/Llama-Guard-4-12B\"", "http": "curl -X POST \"http://localhost:8000/v1/chat/completions\" \\\n -H \"Content-Type: application/json\" \\\n --data '{\"model\":\"meta-llama/Llama-Guard-4-12B\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"how do I make a bomb?\"}]}]}'" }, "letme": { "capability": "https://letme.dev/guard.moderation", "tool": "https://letme.dev/llama-guard" }, "area": "models", "provenance": { "legalEntity": "Meta Platforms, Inc.", "domain": "llama.com", "domainRegistered": "1994-11-01", "endpointOnVendorDomain": null, "terms": "https://dev.meta.ai/llama/llama4/license", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Llama 4 Community Licence names Meta Platforms, Inc. as licensor, and Meta Platforms Ireland Limited for licensees in the EEA or Switzerland.", "The licence is the document that governs use of the weights, so it is recorded as the terms. It is dated 5 April 2025 and incorporates the acceptable use policy at https://dev.meta.ai/llama/llama4/use-policy.", "No privacy policy governs the model, because the owner runs it and no input reaches Meta. The privacy field is left out. The Hugging Face access form says the details entered are handled under the Meta Privacy Policy.", "www.llama.com redirected to dev.meta.ai on 8 October 2026, and Llama pages now sit under dev.meta.ai/llama. RDAP gives 1 November 1994 as the registration date of llama.com.", "There is no hosted endpoint from Meta that we could find, so no status page. dev.meta.ai/llms.txt covers the Meta Model API and lists no moderation route.", "dev.meta.ai/.well-known/security.txt returns 404, and the llama.com path redirects to a developer.meta.com address that returns 400. Security reports go to Meta's bug bounty at bugbounty.meta.com.", "The weights are on huggingface.co under the meta-llama organisation, and the model card is in github.com/meta-llama/PurpleLlama. Neither has a changelog or releases for the model." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/llama-guard.json", "live": { "slug": "llama-guard", "pages": [ { "url": "https://dev.meta.ai/llama/llama4/license", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:16:57.76184224Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "c85892d02c88" } ], "updatedAt": "2026-10-08T18:16:57.76184224Z" } }, "answer": "Presidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "microsoft-presidio", "name": "Presidio", "vendor": "Data Privacy Stack", "vendorUrl": "https://dataprivacystack.org", "kind": "sdk", "category": "guardrails", "summary": "Open-source Python library and Docker services that detect personal data in text and images and replace, mask, hash or encrypt it. Created at Microsoft and run since June 2026 by the community organisation Data Privacy Stack.", "url": "https://www.anchorterminal.com/tools/microsoft-presidio", "markdownUrl": "https://www.anchorterminal.com/tools/microsoft-presidio.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/microsoft-presidio.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/microsoft-presidio.json", "repo": "https://github.com/data-privacy-stack/presidio", "license": "MIT", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "presidio-analyzer" }, { "registry": "pypi", "name": "presidio-anonymizer" }, { "registry": "pypi", "name": "presidio-image-redactor" }, { "registry": "pypi", "name": "presidio" } ], "auth": "none", "authNotes": "None. The Python library runs in the caller's process, and the REST containers accept any caller. The FAQ states the endpoints have no built-in authentication by design and should sit behind a gateway, reverse proxy or service mesh (https://presidio.dataprivacystack.org/faq/). Optional recognisers that call Azure AI Language, Azure Health Data Services or a language model take those services' own credentials.", "pricing": "free", "pricingNotes": "Free under the MIT licence, with no hosted or paid option from the project and no account needed. The cost is the compute to run it, plus any outside service an optional recogniser is configured to call (https://github.com/data-privacy-stack/presidio/blob/main/LICENSE).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 11231, "npmWeekly": null, "pypiWeekly": 1217281, "asOf": "2026-10-08" }, "docsUrl": "https://presidio.dataprivacystack.org", "openapi": "https://presidio.dataprivacystack.org/api-docs/api-docs.yml", "capabilities": [ "guard.pii", "guard.self-host" ], "tags": [ "sdk", "open-source", "self-hosted", "local", "python", "free", "docker", "openapi", "pii", "community-governed" ], "lastRelease": "2026-07-22", "graded": true, "anchor": { "graded": true, "score": 66, "grade": "B", "agentReady": false, "rank": 248, "ranked": true, "rankOf": 722, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 63, "payments": 60, "reliability": 78, "schema": 69, "security": 53, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "MIT-licensed personal data detector with a public OpenAPI document, tests on Python 3.10 to 3.14 and about 1.2 million weekly PyPI downloads. The REST containers have no authentication, the project states no SLA or support, and it covers personal data only, with no prompt injection or content moderation checks.", "bestFor": "Detecting and masking personal data in prompts, outputs, logs and images on the owner's own machines, with detection tuned by entity, threshold and custom recognisers.", "strengths": [ "MIT licence, source on GitHub, and nothing to buy. No account, key or card is needed to install or run it", "OpenAPI 3.0 document for the analyser and anonymiser REST services, with request examples and 400 and 422 error shapes", "CI runs each package on Python 3.10, 3.11, 3.12, 3.13 and 3.14, with CodeQL and Dependabot configured", "Detection is tunable per call with an entity list, a score threshold, an allow list and ad hoc recognisers", "Anonymiser operators cover replace, redact, mask, hash, encrypt and custom functions, and encrypted values can be reversed with the key" ], "weaknesses": [ "The REST containers have no authentication by design. The FAQ says to put a gateway or proxy in front", "SUPPORT.md states no SLA and no official support. The project is run by volunteers since leaving Microsoft", "One release in the 90 days to 8 October 2026 (2.2.364 on 22 July), and CHANGELOG.md has no section for it", "Covers personal data only. No prompt injection, jailbreak or content moderation checks", "The README warns that detection is automated and may miss personal data, so other protections are still needed", "98 open pull requests, and most issues opened since 20 September 2026 had no reply on 8 October" ], "agentNotes": [ "Install from PyPI or pull images from ghcr.io/data-privacy-stack. The mcr.microsoft.com/presidio-* images are no longer updated", "Download a spaCy model (python -m spacy download en_core_web_lg) before the first `AnalyzerEngine()` call, or use the Docker image", "Send both text and language to `/analyze`. A request missing either returns HTTP 500 with a JSON error field", "Pass entities and score_threshold to limit results. Many country-specific recognisers are disabled by default and need enabling in the registry YAML", "Keep the containers on a private network or behind your own authenticating proxy. They accept any caller" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66 } ], "editorialScores": { "ergonomics": 69, "maintenance": 63, "payments": 60, "reliability": 78, "schema": 69, "security": 53, "transparency": 76 }, "provenanceScore": 53 }, "connect": { "install": "pip install presidio-analyzer presidio-anonymizer\npython -m spacy download en_core_web_lg", "http": "docker run -d -p 5002:3000 ghcr.io/data-privacy-stack/presidio-analyzer:latest\ncurl -X POST http://localhost:5002/analyze \\\n -H \"Content-Type: application/json\" \\\n -d '{\"text\": \"My phone number is 555-123-4567.\", \"language\": \"en\"}'" }, "letme": { "capability": "https://letme.dev/guard.pii", "tool": "https://letme.dev/microsoft-presidio" }, "area": "models", "provenance": { "legalEntity": "Data Privacy Stack (community organisation, no legal entity stated)", "domain": "dataprivacystack.org", "domainRegistered": "2026-04-13", "domainNote": "A library and self-hosted containers, not a service. Code is on github.com under the data-privacy-stack organisation and docs on presidio.dataprivacystack.org.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/data-privacy-stack/presidio/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "Presidio was created at Microsoft. The transition notice says it is now a community-governed project under Data Privacy Stack and is not owned or operated by a commercial entity. The blog post announcing the move is dated 29 June 2026.", "github.com/microsoft/presidio answers 301 to github.com/data-privacy-stack/presidio, and microsoft.github.io/presidio shows a moved notice.", "The LICENSE copyright line reads Presidio Contributors. The FAQ says usage terms are the repository's licence and that there is no warranty or SLA.", "No privacy policy was found on dataprivacystack.org or the docs site. Nothing is hosted, so the field is left out.", "security.txt returns 404 on dataprivacystack.org and presidio.dataprivacystack.org. SECURITY.md uses GitHub private vulnerability reporting.", "RDAP gives 2026-04-13 as the registration date of dataprivacystack.org. The repository was created on 4 May 2018." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/microsoft-presidio.json", "live": { "slug": "microsoft-presidio", "pages": [ { "url": "https://raw.githubusercontent.com/data-privacy-stack/presidio/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:24:05.686879193Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "609d3fe25dbc" } ], "updatedAt": "2026-10-08T18:24:05.686879193Z" } }, "facts": [ { "a": "Model API", "b": "SDK + MCP", "name": "Kind" }, { "a": "Meta", "b": "Data Privacy Stack", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Llama 4 Community Licence (source-available weights, not an OSI licence), with the Llama 4 acceptable use policy", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2025-04-29", "b": "2026-07-22", "name": "Last release" }, { "a": "2025-04-05", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "4.4k stars", "b": "11k stars, 1.2M PyPI/wk", "name": "Popularity" } ], "faq": [ { "answer": "Presidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Llama Guard 4 or Presidio?" }, { "answer": "No hosted endpoint is listed for Llama Guard 4. No hosted endpoint is listed for Presidio.", "question": "Can an agent call Llama Guard 4 and Presidio without installing anything?" }, { "answer": "No open-source release is listed for Llama Guard 4. Presidio is open source (MIT).", "question": "Are Llama Guard 4 and Presidio open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "A team outside the EU with a GPU that wants content moderation of text and images on its own hardware, against a fixed 14-category policy it can edit in the prompt.", "slug": "llama-guard", "watchFor": "Weights last changed on 29 April 2025, with no changelog, version tags or stated deprecation policy" }, { "aheadOn": [ "Reliability, 78 against 38", "Schema \u0026 documentation, 69 against 52", "Payments \u0026 pricing, 60 against 45", "Maintenance \u0026 community, 63 against 28", "Transparency \u0026 trust, 65 against 55" ], "also": [ "Open source" ], "goodFor": "Detecting and masking personal data in prompts, outputs, logs and images on the owner's own machines, with detection tuned by entity, threshold and custom recognisers.", "slug": "microsoft-presidio", "watchFor": "The REST containers have no authentication by design. The FAQ says to put a gateway or proxy in front" } ], "job": { "capability": "guard.self-host", "name": "Guard self host" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-llama-guard.json", "title": "Amazon Bedrock Guardrails vs Llama Guard 4", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-llama-guard" }, { "json": "https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-llama-guard.json", "title": "Azure AI Content Safety (Prompt Shields) vs Llama Guard 4", "url": "https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-llama-guard" }, { "json": "https://www.anchorterminal.com/compare/google-model-armor-vs-llama-guard.json", "title": "Google Cloud Model Armor vs Llama Guard 4", "url": "https://www.anchorterminal.com/compare/google-model-armor-vs-llama-guard" }, { "json": "https://www.anchorterminal.com/compare/guardrails-ai-vs-llama-guard.json", "title": "Guardrails AI vs Llama Guard 4", "url": "https://www.anchorterminal.com/compare/guardrails-ai-vs-llama-guard" }, { "json": "https://www.anchorterminal.com/compare/lakera-guard-vs-llama-guard.json", "title": "Lakera Guard (Check Point AI Guardrails) vs Llama Guard 4", "url": "https://www.anchorterminal.com/compare/lakera-guard-vs-llama-guard" }, { "json": "https://www.anchorterminal.com/compare/llama-guard-vs-mistral-moderation.json", "title": "Llama Guard 4 vs Mistral Moderation API", "url": "https://www.anchorterminal.com/compare/llama-guard-vs-mistral-moderation" }, { "json": "https://www.anchorterminal.com/compare/llama-guard-vs-nemo-guardrails.json", "title": "Llama Guard 4 vs NVIDIA NeMo Guardrails", "url": "https://www.anchorterminal.com/compare/llama-guard-vs-nemo-guardrails" }, { "json": "https://www.anchorterminal.com/compare/llama-guard-vs-openai-moderation.json", "title": "Llama Guard 4 vs OpenAI Moderation API", "url": "https://www.anchorterminal.com/compare/llama-guard-vs-openai-moderation" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-microsoft-presidio.json", "title": "Amazon Bedrock Guardrails vs Presidio", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-microsoft-presidio" }, { "json": "https://www.anchorterminal.com/compare/google-model-armor-vs-microsoft-presidio.json", "title": "Google Cloud Model Armor vs Presidio", "url": "https://www.anchorterminal.com/compare/google-model-armor-vs-microsoft-presidio" }, { "json": "https://www.anchorterminal.com/compare/guardrails-ai-vs-microsoft-presidio.json", "title": "Guardrails AI vs Presidio", "url": "https://www.anchorterminal.com/compare/guardrails-ai-vs-microsoft-presidio" }, { "json": "https://www.anchorterminal.com/compare/lakera-guard-vs-microsoft-presidio.json", "title": "Lakera Guard (Check Point AI Guardrails) vs Presidio", "url": "https://www.anchorterminal.com/compare/lakera-guard-vs-microsoft-presidio" }, { "json": "https://www.anchorterminal.com/compare/microsoft-presidio-vs-mistral-moderation.json", "title": "Presidio vs Mistral Moderation API", "url": "https://www.anchorterminal.com/compare/microsoft-presidio-vs-mistral-moderation" }, { "json": "https://www.anchorterminal.com/compare/microsoft-presidio-vs-nemo-guardrails.json", "title": "Presidio vs NVIDIA NeMo Guardrails", "url": "https://www.anchorterminal.com/compare/microsoft-presidio-vs-nemo-guardrails" } ], "scores": [ { "by": 40, "edge": "microsoft-presidio", "key": "reliability", "llama-guard": 38, "microsoft-presidio": 78, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 17, "edge": "microsoft-presidio", "key": "schema", "llama-guard": 52, "microsoft-presidio": 69, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 2, "edge": "microsoft-presidio", "key": "ergonomics", "llama-guard": 67, "microsoft-presidio": 69, "name": "Agent ergonomics", "weight": 13 }, { "by": 0, "edge": "", "key": "security", "llama-guard": 53, "microsoft-presidio": 53, "name": "Security \u0026 auth", "weight": 14 }, { "by": 15, "edge": "microsoft-presidio", "key": "payments", "llama-guard": 45, "microsoft-presidio": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 35, "edge": "microsoft-presidio", "key": "maintenance", "llama-guard": 28, "microsoft-presidio": 63, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 10, "edge": "microsoft-presidio", "key": "transparency", "llama-guard": 55, "microsoft-presidio": 65, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Presidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories. Both do guard self host.", "verdicts": { "llama-guard": "A single self-hosted model classifies text and multi-image prompts against 14 MLCommons-aligned hazard categories and answers in a few tokens. The weights have not changed since 29 April 2025, download access needs Meta's manual approval, and the licence withholds the grant from individuals and companies based in the European Union.", "microsoft-presidio": "MIT-licensed personal data detector with a public OpenAPI document, tests on Python 3.10 to 3.14 and about 1.2 million weekly PyPI downloads. The REST containers have no authentication, the project states no SLA or support, and it covers personal data only, with no prompt injection or content moderation checks." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio", "json": "https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio.md", "slim": "https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio.min.md" }, "markdown": "Presidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories. Both do guard self host.\n\n- Llama Guard 4: grade D, 49.1/100, rank #614 of 722. Markdown https://www.anchorterminal.com/tools/llama-guard.md · JSON https://www.anchorterminal.com/api/v1/tools/llama-guard.json\n- Presidio: grade B, 66/100, rank #248 of 722. Markdown https://www.anchorterminal.com/tools/microsoft-presidio.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-presidio.json\n\n## Which one, for what\n\n### Llama Guard 4 (D)\n\nGood for: A team outside the EU with a GPU that wants content moderation of text and images on its own hardware, against a fixed 14-category policy it can edit in the prompt.\n\nWatch for: Weights last changed on 29 April 2025, with no changelog, version tags or stated deprecation policy\n\n### Presidio (B)\n\nGood for: Detecting and masking personal data in prompts, outputs, logs and images on the owner's own machines, with detection tuned by entity, threshold and custom recognisers.\n\nAhead on:\n- Reliability, 78 against 38\n- Schema \u0026 documentation, 69 against 52\n- Payments \u0026 pricing, 60 against 45\n- Maintenance \u0026 community, 63 against 28\n- Transparency \u0026 trust, 65 against 55\n\nAlso in its favour:\n- Open source\n\nWatch for: The REST containers have no authentication by design. The FAQ says to put a gateway or proxy in front\n\n\n## Score by category\n\n| Category | Weight | Llama Guard 4 | Presidio | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 38 | 78 | Presidio +40 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 52 | 69 | Presidio +17 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 69 | Presidio +2 |\n| Security \u0026 auth | 14% (17.5 this run) | 53 | 53 | even |\n| Payments \u0026 pricing | 10% (12.5 this run) | 45 | 60 | Presidio +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 28 | 63 | Presidio +35 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 55 | 65 | Presidio +10 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **49.1 · D** | **66 · B** | |\n\n## Facts side by side\n\n| Fact | Llama Guard 4 | Presidio |\n| --- | --- | --- |\n| Kind | Model API | SDK + MCP |\n| Vendor | Meta | Data Privacy Stack |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Llama 4 Community Licence (source-available weights, not an OSI licence), with the Llama 4 acceptable use policy | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2025-04-29 | 2026-07-22 |\n| Terms last updated | 2025-04-05 | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | not found in the text | |\n| Terms restrict automated access | not found in the text | |\n| Terms restrict benchmarking | not found in the text | |\n| Terms or service can change without notice | not found in the text | |\n| Arbitration or class-action waiver | not found in the text | |\n| Popularity | 4.4k stars | 11k stars, 1.2M PyPI/wk |\n\n## Verdicts\n\n**Llama Guard 4.** A single self-hosted model classifies text and multi-image prompts against 14 MLCommons-aligned hazard categories and answers in a few tokens. The weights have not changed since 29 April 2025, download access needs Meta's manual approval, and the licence withholds the grant from individuals and companies based in the European Union.\n\n**Presidio.** MIT-licensed personal data detector with a public OpenAPI document, tests on Python 3.10 to 3.14 and about 1.2 million weekly PyPI downloads. The REST containers have no authentication, the project states no SLA or support, and it covers personal data only, with no prompt injection or content moderation checks.\n\n## Before you call either\n\n### Llama Guard 4\n\n1. Request access on the Hugging Face page before anything else. Approval is manual, and the form cannot be edited after submission\n2. Send only the user turn to check an input, and the user turn plus the model's answer to check an output. The template picks the role from the message count\n3. Parse the first line for `safe` or `unsafe` and the second for category codes. Set `max_new_tokens` to about 10 and turn sampling off\n4. Do not send an image with no text. Meta says the model is not an image-only classifier, and S14 is skipped when an image is present\n5. Pair it with a prompt-attack detector. The card says the model can itself be moved by adversarial or injected text\n\n### Presidio\n\n1. Install from PyPI or pull images from ghcr.io/data-privacy-stack. The mcr.microsoft.com/presidio-* images are no longer updated\n2. Download a spaCy model (python -m spacy download en_core_web_lg) before the first `AnalyzerEngine()` call, or use the Docker image\n3. Send both text and language to `/analyze`. A request missing either returns HTTP 500 with a JSON error field\n4. Pass entities and score_threshold to limit results. Many country-specific recognisers are disabled by default and need enabling in the registry YAML\n5. Keep the containers on a private network or behind your own authenticating proxy. They accept any caller\n\n## Questions\n\n### Which is better for AI agents, Llama Guard 4 or Presidio?\n\nPresidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories.\n\n### Can an agent call Llama Guard 4 and Presidio without installing anything?\n\nNo hosted endpoint is listed for Llama Guard 4. No hosted endpoint is listed for Presidio.\n\n### Are Llama Guard 4 and Presidio open source?\n\nNo open-source release is listed for Llama Guard 4. Presidio is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio.json, and with the fewest tokens: https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"llama-guard\", \"b\": \"microsoft-presidio\"}`. From a terminal: `anchor compare llama-guard microsoft-presidio`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/llama-guard.json and https://www.anchorterminal.com/api/v1/tools/microsoft-presidio.json\n\n## Other comparisons with Llama Guard 4 or Presidio\n\n- [Amazon Bedrock Guardrails vs Llama Guard 4](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-llama-guard.md)\n- [Azure AI Content Safety (Prompt Shields) vs Llama Guard 4](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-llama-guard.md)\n- [Google Cloud Model Armor vs Llama Guard 4](https://www.anchorterminal.com/compare/google-model-armor-vs-llama-guard.md)\n- [Guardrails AI vs Llama Guard 4](https://www.anchorterminal.com/compare/guardrails-ai-vs-llama-guard.md)\n- [Lakera Guard (Check Point AI Guardrails) vs Llama Guard 4](https://www.anchorterminal.com/compare/lakera-guard-vs-llama-guard.md)\n- [Llama Guard 4 vs Mistral Moderation API](https://www.anchorterminal.com/compare/llama-guard-vs-mistral-moderation.md)\n- [Llama Guard 4 vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/llama-guard-vs-nemo-guardrails.md)\n- [Llama Guard 4 vs OpenAI Moderation API](https://www.anchorterminal.com/compare/llama-guard-vs-openai-moderation.md)\n- [Amazon Bedrock Guardrails vs Presidio](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-microsoft-presidio.md)\n- [Google Cloud Model Armor vs Presidio](https://www.anchorterminal.com/compare/google-model-armor-vs-microsoft-presidio.md)\n- [Guardrails AI vs Presidio](https://www.anchorterminal.com/compare/guardrails-ai-vs-microsoft-presidio.md)\n- [Lakera Guard (Check Point AI Guardrails) vs Presidio](https://www.anchorterminal.com/compare/lakera-guard-vs-microsoft-presidio.md)\n- [Presidio vs Mistral Moderation API](https://www.anchorterminal.com/compare/microsoft-presidio-vs-mistral-moderation.md)\n- [Presidio vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/microsoft-presidio-vs-nemo-guardrails.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Llama Guard 4 vs Presidio", "url": "" } ], "description": "Presidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories. Both do guard self host. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Llama Guard 4 D 49.1", "Presidio B 66", "scores" ], "h1": "Llama Guard 4 vs Presidio", "image": "https://www.anchorterminal.com/assets/og/compare-llama-guard-vs-microsoft-presidio.png", "path": "/compare/llama-guard-vs-microsoft-presidio", "published": "2026-10-01", "section": "tools", "title": "Llama Guard 4 vs Presidio for AI agents, D 49.1 vs B 66", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/llama-guard-vs-microsoft-presidio" }, "tokens": { "markdown": 2250, "slim": 630 }, "version": 1 }