The model card documents refusal policy, input filters, and jailbreak-style adversarial testing, but self-harm remains a refusal/filter class rather than a first-class risk domain.
Contents
Summary
Grok 4.1 Model Card is a model card from xAI dated November 17, 2025. The model card documents refusal policy, input filters, and jailbreak-style adversarial testing, but self-harm remains a refusal/filter class rather than a first-class risk domain.
Representation
This document codes self-harm as subdomain with evaluative-object status operationally_underspecified. The public crosswalk records self-harm naming as explicit and mechanism coverage as GEN; DET; JB.
| Field | Value |
|---|---|
| Organization | xAI |
| Document type | model_card |
| Document genre | product_safety_artifact |
| Risk status | Class III |
| First-class equivalence | no |
| Threshold mechanism | none |
| Deployment consequence | none |
| Multi-turn evaluation | none |
Assessment
The retained crosswalk places this document at Class III. That classification reflects what the document itself operationalizes publicly, not the organization's overall internal practice.
Related pages
Use the linked provider, methods, and neighboring governance pages below to place this document in context.
Sources
The primary public source for this page is https://data.x.ai/2025-11-17-grok-4-1-model-card.pdf. The coded evidence excerpt is: we employ input filters to reject specific classes of sensitive requests, such as those involving bioweapons, chemical weapons, self-harm, and child sexual abuse material..
This page is grounded in the DOI policy registry, the policy coding manual, and the document's own public URL.
Access publication
Safety note
This publication preserves a harm-minimization posture and does not provide self-harm instructions. If you or someone you know is in immediate danger, call your local emergency number. In the U.S. and Canada, call or text 988.