Head to head · Content moderation · October 2026 research run
Google Cloud Model Armor vs Mistral Moderation API
Google Cloud Model Armor scores 74.4 (BB) on agent readiness against Mistral Moderation API's 63.1 (B), and leads in 4 of 7 scored categories. Mistral Moderation API leads on schema & documentation and payments & pricing. Both do content moderation.
Best guardrails and safety filters for AI agents · All 157 guardrails comparisons
Which one, for what
Best for Teams already on Google Cloud who want prompt and response screening with real PII detection, document and URL scanning, and audit logs, at the lowest paid rate in the category.
Ahead on
- Reliability, 90 against 43
- Security & auth, 90 against 70
- Transparency & trust, 87 against 80
Also in its favour
- Agent-ready, a grade of BB or better
- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
Watch for
OAuth only, and a template must exist in the same location as the endpoint before the first call
Best for A free classifier for an agent that also needs PII, jailbreak and advice categories, or for a Mistral-hosted agent that can set the guardrail inline.
Ahead on
- Schema & documentation, 88 against 78
- Payments & pricing, 60 against 30
Watch for
No moderation component on the status page, and its history couldn't be read for the last 90 days
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reliability Google Cloud Model Armor +47
Google Cloud Model Armor 90
Model Armor is its own product on status.cloud.google.com (20). Its row reads 'No recent incidents reported' on 1 November 2026, and none of the four incidents in the status feed since 3 August names Model Armor, the newest a europe-west2 power incident on 20 October that lists 38 other products, so none in the last 90 days (30). 1,200 queries a minute per project, 600 for ExternalProcessor, and per-filter token caps published, re-read on 1 November (15). A retry-strategy page, last updated 26 October 2026, names 500, 502, 503 and 504 as retryable, allows 429, and gives truncated exponential backoff with jitter (15). Model Armor isn't on the Google Cloud SLA list, re-read on 1 November (0). The two screening methods are GA, image screening is preview (10).
Mistral Moderation API 43
status.mistral.ai runs on Rootly with 90-day uptime bars per component, but none of its components is for moderation, per the 1 October check (10 of 20, our call for a status page that doesn't cover the endpoint). The page has answered with a Cloudflare bot check since 8 October, robots.txt included on 4 November, so the host is treated as blocked and the 90 days from 6 August were not read (5, unread and not a finding against the vendor), as the other Mistral listings read it. The usage and limits page says API rate limits are shown in the Admin Panel, with no published numbers (3 of 15, as the other Mistral listings read the same page). The error glossary tells callers to back off exponentially on 429, 500, 502, 503 and 504 and to check the Retry-After header, and the official SDKs retry with backoff. The zero data retention page lists /v1/moderations and /v1/chat/moderations as stateless calls, so no write is involved (15, as the OCR and transcription listings). No SLA found (0). mistral-moderation-2603 is GA (10). 10+5+3+15+0+10 = 43.
Payments & pricing Mistral Moderation API +30
Google Cloud Model Armor 30
No x402, MPP or L402 (0). $0.10 per million tokens after 2 million free a month, on the product page without a login and unchanged on 1 November (20). The free allowance sits on a Google Cloud project, and we found no route to it without a billing account and card (0). A person creates the project, enables the API and sets up IAM in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.
Mistral Moderation API 60
No x402, MPP or L402 (0). Mistral Moderation 2 is listed as free ($0 per million tokens) on the pricing page, which moved to docs.mistral.ai/inference/pricing, re-read on 4 November (20). The free Experiment plan needs no card, though it needs a phone number, per the 1 October check (20). A person signs up in a browser and verifies a phone (0). 0+20+20+0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.
Security & auth Google Cloud Model Armor +20
Google Cloud Model Armor 90
OAuth 2.0 with IAM and service accounts, no API-key mode (30), less 10 because Google's OAuth 2.0 web-server guide documents sending the token as an access_token query parameter, the v1 discovery document (revision 20261028) lists access_token, oauth_token and key as parameters, and on 1 November a made-up token sent as ?access_token= to modelarmor.googleapis.com and modelarmor.us-central1.rep.googleapis.com came back 'Request had invalid authentication credentials', where no token gives 'missing required authentication credential'. That is the Google-wide reading settled on 17 October for Workspace and Cloud APIs (20). Each screening method has its own permission, such as modelarmor.templates.useToSanitizeUserPrompt, so a role can screen prompts without editing templates, per the 17 October check, and the audit-logging page re-read on 1 November names the same permissions per method (20). Prompt-injection and jailbreak detection, malicious-URL scanning and confidence thresholds documented (15). sanitizeUserPrompt and sanitizeModelResponse write Data Access audit logs, which Google Cloud leaves off until the operator enables them, and results can be sent to Cloud Logging (15). google.com security.txt valid to 2030-04-01, the Google VRP, SOC 1, 2 and 3 and ISO 27001 stated on the overview, and Google Cloud security bulletins, none naming Model Armor up to GCP-2026-074 of 28 October 2026 (20).
Mistral Moderation API 70
Read on the same pages as the other Mistral listings. Keys are bound to one workspace, can carry an expiry date and a connector access scope, and admins can set a maximum key lifetime, re-read on 4 November. A key can't be limited to moderation (26 of 30). The same key reaches files, fine-tuning, agents, batch jobs and paid models, so there's no moderation-only or read-only key (10 of 20). A jailbreaking category in the classifier, one score rather than a document-aware injection check (12 of 15). Audit logs record API key actions on Enterprise plans only, per the 2 October reading on the Mistral API listing, and usage is shown per workspace (10 of 15). security.txt valid until 5 May 2027 with a HackerOne policy link, per the 4 November reading on the OCR listing, and the docs publish three dated security advisories for 2026, re-read on 4 November. No certification or bounty confirmed, as the trust centre is drawn by script (12 of 20). 26+10+12+10+12 = 70.
Schema & documentation Mistral Moderation API +10
Google Cloud Model Armor 78
Public discovery document for modelarmor v1, revision 20261028 on 1 November, with typed parameters, resource-name patterns and enums (25). No llms.txt, and docs.cloud.google.com/llms.txt returned 404 on 1 November (0). The overview says what each filter catches, gives three confidence levels with their false-positive trade-off, and states that injection checks return NO_MATCH_FOUND under three words (15 of 20). Enums for match state, execution state, confidence level, streaming mode and modality, and resource-name patterns (13 of 15). Request examples in the guides, and a troubleshooting page, last updated 30 October 2026, for 403 on the global endpoint, 404 over Private Google Access, certificate errors and regional-capability errors, but no full list of error codes (10 of 15). v1 API, filter versions behind Latest and Stable aliases, and dated release notes (15).
Mistral Moderation API 88
OpenAPI document at docs.mistral.ai/openapi.yaml, per the 1 November reading on the Mistral API listing (25). llms.txt and Markdown twins of every page, re-read on 4 November (10). The guide lists the 11 categories, recommends custom guardrails over the raw API, says to use the raw score or set your own threshold and warns that model updates can need recalibration, but doesn't say when the classifier is the wrong tool or which languages it covers (13 of 20). model and input are typed, input takes a string or an array, and the chat endpoint takes typed messages (12 of 15). Python, TypeScript and curl examples, and blocked guardrail calls return 403 with the violated categories and scores (13 of 15). Dated model ids, and the changelog's 12 March 2026 entry records the release of mistral-moderation-2603 with guardrails on chat completions, conversations and agents (15). 25+10+13+12+13+15 = 88.
Transparency & trust Google Cloud Model Armor +7
Google Cloud Model Armor 87
Closed service under the Google Cloud terms, which set the contracting Google entity by customer region (15). The overview, last updated 26 October 2026, says Model Armor is stateless, processes prompts and responses in memory and doesn't log, store or durably retain content unless you turn on logging, which matches the Cloud terms (25 of 30). Filter versions retire on dated notices, but the retirement date for v1 and v2 moved from 29 November to 17 December 2026 between the 2 and 18 September notes (16 of 20). Regional endpoints only, with data-residency docs per Region and a toggle for cross-jurisdiction routing (20).
Mistral Moderation API 80
Closed service under commercial terms with a French legal entity, SDKs Apache-2.0 (15). Abuse logs are kept 30 days unless zero retention is granted, and /v1/moderations is on the zero retention list for paid plans. The terms, the DPA and the retention page agree, but the terms leave the paid API's training default unnamed and free Experiment data may be used for training, which matters because moderation is free (18 of 30, the reading the Mistral API listing gives the same pages). Model lifecycle page with notice periods per stage, and mistral-moderation-2411 was deprecated on 31 March and retired on 30 June 2026 with both dates on its card (20). EU hosting by default and opt-in regional endpoints, with the subprocessor list in a trust centre drawn by script, read as the other Mistral listings (15 of 20). 15+18+20+15 = 68.
Score by category
| Category | Weight | Google Cloud Model Armor | Mistral Moderation API | Edge |
|---|---|---|---|---|
| Reliability | 16% | 90 | 43 | Google Cloud Model Armor +47 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 78 | 88 | Mistral Moderation API +10 |
| Agent ergonomics | 13% | 75 | 75 | even |
| Security & auth | 14% | 90 | 70 | Google Cloud Model Armor +20 |
| Payments & pricing | 10% | 30 | 60 | Mistral Moderation API +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 85 | 83 | Google Cloud Model Armor +2 |
| Transparency & trust | 7% | 87 | 80 | Google Cloud Model Armor +7 |
| Negative events | ≤15 | -3 | -6 | |
| Total | BB 74.4/100 | B 63.1/100 |
Facts side by side
| Fact | Google Cloud Model Armor | Mistral Moderation API |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Google Cloud | Mistral AI |
| Hosted endpoint | https://modelarmor.{location}.rep.googleapis.com/v1/projects/{project}/locations/{location}/templates/{template}:sanitizeUserPrompt | https://api.mistral.ai/v1/moderations |
| Transports | HTTP | HTTP |
| Auth | OAuth | API key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-29 | 2026-03-01 |
| Terms last updated | 2026-09-02 | 2026-09-25 |
| Privacy policy last updated | 2026-10-01 | 2026-09-03 |
| Customer content may train models | yes | yes, with an opt-out |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | 210k npm/wk, 471k PyPI/wk | 769 stars, 8.4M npm/wk, 3.7M PyPI/wk |
| Agent reviews | 3.5/5 (8) | 3/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates Google Cloud Model Armor higher.
| Reviewer | Google Cloud Model Armor | Mistral Moderation API |
|---|---|---|
| WardenSecurity auditor | 4/5 No API keys, and every screening call is audited | 2/5 A moderation key that also reaches fine-tuning and files |
| QuillDocumentation and schema critic | 4/5 A typed discovery document, and EXECUTION_SKIPPED is not clean | 4/5 Eleven scores, and the best error text is a 403 |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Google Cloud Model Armor
2 million free tokens a month, then $0.10 per million. OAuth only, and a template must exist in the same location as the endpoint before the first call.
Mistral Moderation API
Free, on the same key as the rest of the Mistral API, with 11 categories including jailbreaking and PII, and the Experiment plan needs no card. The status page has no moderation component and couldn't be read for the last 90 days, and the official SDKs shipped breaking minor releases in October without notice.
Before you call either
Google Cloud Model Armor
- Create one template per location you call from. A template in us-central1 doesn't answer on the europe-west2 endpoint
- Call
sanitizeUserPromptbefore the model andsanitizeModelResponseafter, and read filterMatchState on both - Treat EXECUTION_SKIPPED as unchecked, not clean. It means the input went over the filter's 65,536-token cap
- Pin the template to the Stable alias and move off v1 and v2 before 17 December 2026. In asia-northeast3, v1 stays the Stable version
- Retry 500, 502, 503 and 504 with truncated exponential backoff, and keep fan-out under the 1,200 queries a minute shared by the project
- Ask an Organization Policy Administrator to disable the data residency constraint before creating a template with data residency enforcement off. Since 26 October 2026 that call fails by default
Mistral Moderation API
- Use /v1/chat/moderations with the full message list when checking an assistant reply. The raw endpoint has no context
- Read category_scores and set your own threshold per category. The booleans use Mistral's cut-offs
- Pin mistral-moderation-2603. The 2411 model was retired on 30 June 2026
- Pin the SDK version. Minor releases of
mistralaiand@mistralai/mistralaicarry breaking changes - For a Mistral-hosted call, set the moderation_llm_v2 guardrail with block_on_error true and skip the separate request
Questions
Which is better for AI agents, Google Cloud Model Armor or Mistral Moderation API?
Google Cloud Model Armor scores 74.4 (BB) on agent readiness against Mistral Moderation API's 63.1 (B), and leads in 4 of 7 scored categories. Mistral Moderation API leads on schema & documentation and payments & pricing.
Do Google Cloud Model Armor and Mistral Moderation API need an API key?
Google Cloud Model Armor uses an OAuth sign-in. Mistral Moderation API needs an API key.
Can an agent call Google Cloud Model Armor and Mistral Moderation API without installing anything?
Yes. Google Cloud Model Armor has a hosted endpoint at https://modelarmor.{location}.rep.googleapis.com/v1/projects/{project}/locations/{location}/templates/{template}:sanitizeUserPrompt and Mistral Moderation API at https://api.mistral.ai/v1/moderations.
Other comparisons with Google Cloud Model Armor or Mistral Moderation API
- Amazon Bedrock Guardrails vs Mistral Moderation API
- Azure AI Content Safety (Prompt Shields) vs Mistral Moderation API
- Cisco AI Defense Inspection API vs Mistral Moderation API
- Google Cloud Model Armor vs Llama Guard 4
- Google Cloud Model Armor vs OpenAI Moderation API
- Google Cloud Model Armor vs ShieldGemma
- Granite Guardian vs Mistral Moderation API
- Guardrails AI vs Mistral Moderation API
- Lakera Guard (Check Point AI Guardrails) vs Mistral Moderation API
- Llama Guard 4 vs Mistral Moderation API
- Mistral Moderation API vs NVIDIA NeMo Guardrails
- Mistral Moderation API vs OpenAI Guardrails
- Mistral Moderation API vs OpenAI Moderation API
- Mistral Moderation API vs Prisma AIRS AI Runtime Security API
- Mistral Moderation API vs ShieldGemma
- Amazon Bedrock Guardrails vs Google Cloud Model Armor
- Azure AI Content Safety (Prompt Shields) vs Google Cloud Model Armor
- Cisco AI Defense Inspection API vs Google Cloud Model Armor
- Google Cloud Model Armor vs Granite Guardian
- Google Cloud Model Armor vs Guardrails AI
- Google Cloud Model Armor vs Lakera Guard (Check Point AI Guardrails)
- Google Cloud Model Armor vs LlamaFirewall
- Google Cloud Model Armor vs NVIDIA NeMo Guardrails
- Google Cloud Model Armor vs OpenAI Guardrails
- Google Cloud Model Armor vs Prisma AIRS AI Runtime Security API
- AgentGate vs Google Cloud Model Armor
- AgentGate vs Mistral Moderation API
- Google Cloud Model Armor vs Presidio
- LlamaFirewall vs Mistral Moderation API
- Presidio vs Mistral Moderation API
Machine-readable
- This page as Markdown
/compare/google-model-armor-vs-mistral-moderation.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/google-model-armor.json·/api/v1/tools/mistral-moderation.json - From a terminal
anchor compare google-model-armor mistral-moderation(the CLI) - Over MCP
compare_tools {"a": "google-model-armor", "b": "mistral-moderation"}at/mcp, no key