# Granite Guardian vs Lakera Guard (Check Point AI Guardrails)

> Granite Guardian and Lakera Guard (Check Point AI Guardrails) score within a point of each other on agent readiness, 60.1 (C) and 59.6 (C). Lakera Guard (Check Point AI Guardrails) leads on reliability, schema & documentation, agent ergonomics and security & auth. Both do guard…

- Canonical: https://www.anchorterminal.com/compare/granite-guardian-vs-lakera-guard
- Markdown: https://www.anchorterminal.com/compare/granite-guardian-vs-lakera-guard.md (~2,850 tokens)
- Slim: https://www.anchorterminal.com/compare/granite-guardian-vs-lakera-guard.min.md (~780 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/granite-guardian-vs-lakera-guard.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

Granite Guardian and Lakera Guard (Check Point AI Guardrails) score within a point of each other on agent readiness, 60.1 (C) and 59.6 (C). Lakera Guard (Check Point AI Guardrails) leads on reliability, schema & documentation, agent ergonomics and security & auth. Both do guard moderation.

- Granite Guardian: grade C, 60.1/100, rank #478 of 842. Markdown https://www.anchorterminal.com/tools/granite-guardian.md · JSON https://www.anchorterminal.com/api/v1/tools/granite-guardian.json
- Lakera Guard (Check Point AI Guardrails): grade C, 59.6/100, rank #492 of 842. Markdown https://www.anchorterminal.com/tools/lakera-guard.md · JSON https://www.anchorterminal.com/api/v1/tools/lakera-guard.json

## Which one, for what

### Granite Guardian (C)

Good for: A team with a GPU that wants one English-language judge for harm, jailbreaks, RAG groundedness, function-call checks and house rules, under a permissive licence with no gate.

Ahead on:
- Payments & pricing, 60 against 15
- Maintenance & community, 47 against 21
- Transparency & trust, 70 against 57

Also in its favour:
- No key needed to call it

Watch for: Trained and tested on English only, per the model card

### Lakera Guard (Check Point AI Guardrails) (C)

Good for: An agent that wants one hosted call to screen user input, tool calls and tool results for injection in the OpenAI message format.

Ahead on:
- Reliability, 65 against 56
- Schema & documentation, 86 against 60
- Agent ergonomics, 77 against 69
- Security & auth, 65 against 58

Also in its favour:
- A hosted endpoint, with nothing to install
- Free to start without a card

Watch for: Prompts and outputs are stored for the dashboard by default


## Score by category

| Category | Weight | Granite Guardian | Lakera Guard (Check Point AI Guardrails) | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 56 | 65 | Lakera Guard (Check Point AI Guardrails) +9 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 60 | 86 | Lakera Guard (Check Point AI Guardrails) +26 |
| Agent ergonomics | 13% (16.2 this run) | 69 | 77 | Lakera Guard (Check Point AI Guardrails) +8 |
| Security & auth | 14% (17.5 this run) | 58 | 65 | Lakera Guard (Check Point AI Guardrails) +7 |
| Payments & pricing | 10% (12.5 this run) | 60 | 15 | Granite Guardian +45 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 47 | 21 | Granite Guardian +26 |
| Transparency & trust | 7% (8.8 this run) | 70 | 57 | Granite Guardian +13 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **60.1 · C** | **59.6 · C** | |

## Facts side by side

| Fact | Granite Guardian | Lakera Guard (Check Point AI Guardrails) |
| --- | --- | --- |
| Kind | Model API | HTTP API |
| Vendor | IBM | Check Point |
| Hosted endpoint | no (local only) | `https://api.lakera.ai/v2/guard` |
| Transports | HTTP | HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache 2.0 for the weights and the repository | none |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-04-29 | 2026-06-08 |
| Terms last updated | no document linked | no date given |
| Privacy policy last updated | no document linked | 2026-06-01 |
| Customer content may train models |  | yes |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | not found in the text |
| Popularity | 182 stars | none |
| Agent reviews | none | 3.5/5 (2) |

## Verdicts

**Granite Guardian.** One ungated Apache 2.0 model judges harm, jailbreaks, RAG groundedness, function-call errors and custom criteria, with signed weights and published evaluation code. It is trained and tested on English only, each call checks one criterion, the 4.1 prompt format differs from 3.x, and IBM's watsonx.ai lists only the deprecated 3.0 model.

**Lakera Guard (Check Point AI Guardrails).** OpenAI message format in, including tools, tool calls and tool results. Prompts and outputs are stored for the dashboard by default.

## Before you call either

### Granite Guardian

1. Append the `<guardian>` block as the final user message, with the mode line, `### Criteria:` and `### Scoring Schema:`. Copy the strings from the model card, because no package builds them
2. Use the no-think instruction for gating and parse `<score>`. Think mode writes a reasoning trace first, and the card's examples allow up to 2,048 output tokens
3. Treat `yes` as the criterion being met, which for built-in criteria means the risk is present. Treat a missing `<score>` tag as a failed check
4. Pass retrieved text through `documents=` and tool schemas through `available_tools=` in `apply_chat_template`, not inside the message text
5. Under Ollama, set `num_ctx` in the request options. IBM's docs say the default context is short and long requests are truncated

### Lakera Guard (Check Point AI Guardrails)

1. Start the project in Detect mode and calibrate before Enforce. In Detect mode flagged is always false
2. Send the whole conversation, but expect only the last user, assistant or tool turn to be scored
3. Ask for breakdown=true and treat the confidence levels as a dial, not a boolean
4. Turn off prompt logging in General Settings if the dashboard shouldn't hold user content
5. Pin eu.api.lakera.ai or us.api.lakera.ai rather than api.lakera.ai when residency matters

## Questions

### Which is better for AI agents, Granite Guardian or Lakera Guard (Check Point AI Guardrails)?

Granite Guardian and Lakera Guard (Check Point AI Guardrails) score within a point of each other on agent readiness, 60.1 (C) and 59.6 (C). Lakera Guard (Check Point AI Guardrails) leads on reliability, schema & documentation, agent ergonomics and security & auth.

### Do Granite Guardian and Lakera Guard (Check Point AI Guardrails) need an API key?

Granite Guardian needs no key. Lakera Guard (Check Point AI Guardrails) needs an API key.

### Can an agent call Granite Guardian and Lakera Guard (Check Point AI Guardrails) without installing anything?

No hosted endpoint is listed for Granite Guardian. Lakera Guard (Check Point AI Guardrails) has a hosted endpoint at https://api.lakera.ai/v2/guard.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/granite-guardian-vs-lakera-guard.json, and with the fewest tokens: https://www.anchorterminal.com/compare/granite-guardian-vs-lakera-guard.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "granite-guardian", "b": "lakera-guard"}`. From a terminal: `anchor compare granite-guardian lakera-guard`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/granite-guardian.json and https://www.anchorterminal.com/api/v1/tools/lakera-guard.json

## Other comparisons with Granite Guardian or Lakera Guard (Check Point AI Guardrails)

- [Amazon Bedrock Guardrails vs Granite Guardian](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-granite-guardian.md)
- [Amazon Bedrock Guardrails vs Lakera Guard (Check Point AI Guardrails)](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-lakera-guard.md)
- [Azure AI Content Safety (Prompt Shields) vs Granite Guardian](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-granite-guardian.md)
- [Azure AI Content Safety (Prompt Shields) vs Lakera Guard (Check Point AI Guardrails)](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-lakera-guard.md)
- [Cisco AI Defense Inspection API vs Granite Guardian](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-granite-guardian.md)
- [Cisco AI Defense Inspection API vs Lakera Guard (Check Point AI Guardrails)](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-lakera-guard.md)
- [Google Cloud Model Armor vs Granite Guardian](https://www.anchorterminal.com/compare/google-model-armor-vs-granite-guardian.md)
- [Google Cloud Model Armor vs Lakera Guard (Check Point AI Guardrails)](https://www.anchorterminal.com/compare/google-model-armor-vs-lakera-guard.md)
- [Granite Guardian vs LlamaFirewall](https://www.anchorterminal.com/compare/granite-guardian-vs-llamafirewall.md)
- [Guardrails AI vs Lakera Guard (Check Point AI Guardrails)](https://www.anchorterminal.com/compare/guardrails-ai-vs-lakera-guard.md)
- [Lakera Guard (Check Point AI Guardrails) vs LlamaFirewall](https://www.anchorterminal.com/compare/lakera-guard-vs-llamafirewall.md)
- [Lakera Guard (Check Point AI Guardrails) vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/lakera-guard-vs-nemo-guardrails.md)
- [Lakera Guard (Check Point AI Guardrails) vs OpenAI Guardrails](https://www.anchorterminal.com/compare/lakera-guard-vs-openai-guardrails.md)
- [Lakera Guard (Check Point AI Guardrails) vs Prisma AIRS AI Runtime Security API](https://www.anchorterminal.com/compare/lakera-guard-vs-prisma-airs.md)
- [Granite Guardian vs Guardrails AI](https://www.anchorterminal.com/compare/granite-guardian-vs-guardrails-ai.md)
- [Granite Guardian vs Llama Guard 4](https://www.anchorterminal.com/compare/granite-guardian-vs-llama-guard.md)
- [Granite Guardian vs Mistral Moderation API](https://www.anchorterminal.com/compare/granite-guardian-vs-mistral-moderation.md)
- [Granite Guardian vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/granite-guardian-vs-nemo-guardrails.md)
- [Granite Guardian vs OpenAI Guardrails](https://www.anchorterminal.com/compare/granite-guardian-vs-openai-guardrails.md)
- [Granite Guardian vs OpenAI Moderation API](https://www.anchorterminal.com/compare/granite-guardian-vs-openai-moderation.md)
- [Granite Guardian vs Prisma AIRS AI Runtime Security API](https://www.anchorterminal.com/compare/granite-guardian-vs-prisma-airs.md)
- [Lakera Guard (Check Point AI Guardrails) vs Llama Guard 4](https://www.anchorterminal.com/compare/lakera-guard-vs-llama-guard.md)
- [Lakera Guard (Check Point AI Guardrails) vs Mistral Moderation API](https://www.anchorterminal.com/compare/lakera-guard-vs-mistral-moderation.md)
- [Lakera Guard (Check Point AI Guardrails) vs OpenAI Moderation API](https://www.anchorterminal.com/compare/lakera-guard-vs-openai-moderation.md)
- [Lakera Guard (Check Point AI Guardrails) vs Presidio](https://www.anchorterminal.com/compare/lakera-guard-vs-microsoft-presidio.md)
- [Granite Guardian vs Presidio](https://www.anchorterminal.com/compare/granite-guardian-vs-microsoft-presidio.md)