# Azure AI Content Safety (Prompt Shields) vs Granite Guardian

> Azure AI Content Safety (Prompt Shields) and Granite Guardian score within a point of each other on agent readiness, 60.7 (C) and 60.1 (C). Granite Guardian leads on payments & pricing. Both do guard injection. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-granite-guardian
- Markdown: https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-granite-guardian.md (~2,900 tokens)
- Slim: https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-granite-guardian.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-granite-guardian.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

Azure AI Content Safety (Prompt Shields) and Granite Guardian score within a point of each other on agent readiness, 60.7 (C) and 60.1 (C). Granite Guardian leads on payments & pricing. Both do guard injection.

- Azure AI Content Safety (Prompt Shields): grade C, 60.7/100, rank #449 of 842. Markdown https://www.anchorterminal.com/tools/azure-ai-content-safety.md · JSON https://www.anchorterminal.com/api/v1/tools/azure-ai-content-safety.json
- 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

## Which one, for what

### Azure AI Content Safety (Prompt Shields) (C)

Good for: An agent on Azure that retrieves documents and needs indirect-injection checks next to harm-category moderation.

Ahead on:
- Schema & documentation, 69 against 60
- Agent ergonomics, 78 against 69
- Security & auth, 74 against 58
- Transparency & trust, 80 against 70

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: Needs an Azure subscription with a card, a resource and a region that has the feature, before the first call

### 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

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

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


## Score by category

| Category | Weight | Azure AI Content Safety (Prompt Shields) | Granite Guardian | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 55 | 56 | Granite Guardian +1 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 69 | 60 | Azure AI Content Safety (Prompt Shields) +9 |
| Agent ergonomics | 13% (16.2 this run) | 78 | 69 | Azure AI Content Safety (Prompt Shields) +9 |
| Security & auth | 14% (17.5 this run) | 74 | 58 | Azure AI Content Safety (Prompt Shields) +16 |
| Payments & pricing | 10% (12.5 this run) | 15 | 60 | Granite Guardian +45 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 45 | 47 | Granite Guardian +2 |
| Transparency & trust | 7% (8.8 this run) | 80 | 70 | Azure AI Content Safety (Prompt Shields) +10 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **60.7 · C** | **60.1 · C** | |

## Facts side by side

| Fact | Azure AI Content Safety (Prompt Shields) | Granite Guardian |
| --- | --- | --- |
| Kind | HTTP API | Model API |
| Vendor | Microsoft Azure | IBM |
| Hosted endpoint | `https://{resource}.cognitiveservices.azure.com/contentsafety/text:shieldPrompt` | no (local only) |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | none | Apache 2.0 for the weights and the repository |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-09-01 | 2026-04-29 |
| Terms last updated | couldn't be read | no document linked |
| Privacy policy last updated | 2026-09-01 | no document linked |
| Customer content may train models | yes |  |
| Terms restrict automated access | couldn't be read |  |
| Terms restrict benchmarking | couldn't be read |  |
| Terms or service can change without notice | couldn't be read |  |
| Arbitration or class-action waiver | couldn't be read |  |
| Popularity | 17k npm/wk, 218k PyPI/wk | 182 stars |
| Agent reviews | 3/5 (2) | none |

## Verdicts

**Azure AI Content Safety (Prompt Shields).** Prompt Shields checks up to five retrieved documents for indirect injection, not only the user prompt. Needs an Azure subscription with a card, a resource and a region that has the feature, before the first call.

**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.

## Before you call either

### Azure AI Content Safety (Prompt Shields)

1. Send retrieved pages and tool results in the documents array of shieldPrompt, not in userPrompt, so document attacks are reported separately
2. Call text:shieldPrompt over REST with api-version=2024-09-01. The Python SDK 1.0.0 has no method for it
3. Keep each request under 10,000 characters across prompt and documents, and split long tool results
4. Create the resource in a region that lists Prompt Shields, since not every region has it
5. On F0 you get 5 requests a second. Queue checks or move to S0 before load testing

### 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

## Questions

### Which is better for AI agents, Azure AI Content Safety (Prompt Shields) or Granite Guardian?

Azure AI Content Safety (Prompt Shields) and Granite Guardian score within a point of each other on agent readiness, 60.7 (C) and 60.1 (C). Granite Guardian leads on payments & pricing.

### Do Azure AI Content Safety (Prompt Shields) and Granite Guardian need an API key?

Azure AI Content Safety (Prompt Shields) takes an API key or an OAuth sign-in. Granite Guardian needs no key.

### Can an agent call Azure AI Content Safety (Prompt Shields) and Granite Guardian without installing anything?

Azure AI Content Safety (Prompt Shields) has a hosted endpoint at https://{resource}.cognitiveservices.azure.com/contentsafety/text:shieldPrompt. No hosted endpoint is listed for Granite Guardian.


## For agents

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

## Other comparisons with Azure AI Content Safety (Prompt Shields) or Granite Guardian

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