> For the complete documentation index, see [llms.txt](https://docs.sea-lion.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sea-lion.ai/models/sea-guard.md). # SEA-GUARD **SEA-Guard**, released on **4 Feb 2026**, is our premier suite of safety and moderation models tailored for the Southeast Asian landscape. This collection focuses on robust visual and textual guardrails, ensuring AI deployments remain secure and culturally compliant across the region. ## The SEA-Guard Collection The SEA-Guard suite currently consists of 4 specialized models: * [**Qwen-SEA-Guard-4B**](/models/sea-guard/qwennllama-sea-guard.md) (`https://huggingface.co/aisingapore/Qwen-SEA-Guard-4B-040226`) is a **4B Image-to-Text** model serving as a lightweight visual safety guardrail, specifically optimized for efficient edge applications where low latency is critical. * [**Qwen-SEA-Guard-8B**](/models/sea-guard/qwennllama-sea-guard.md) (`https://huggingface.co/aisingapore/Qwen-SEA-Guard-8B-040226`) is an **8B Image-to-Text** model that offers a balanced visual moderation solution with stronger reasoning capabilities for more nuanced content detection. * [**Llama-SEA-Guard-8B**](/models/sea-guard/qwennllama-sea-guard.md) (`https://huggingface.co/aisingapore/Llama-SEA-Guard-8B-040226`) is an **8B Text Generation** model. This text-only safety specialist is optimized for chat moderation and policy enforcement, ensuring safe interactions in dialogue systems. * [**Gemma-SEA-Guard-12B**](/models/sea-guard/gemma-sea-guard.md) (`https://huggingface.co/aisingapore/Gemma-SEA-Guard-12B-040226`) is a high-capacity **12B Image-Text-to-Text** multimodal safety model designed for complex content analysis, capable of interpreting intricate relationships between visual and textual data. ## Our Commitment to Safe Regional AI The SEA-Guard collection advances our mission to build AI that is not only culturally intelligent but also inherently safe. By providing specialized guardrails for both text and vision, these models enable developers to deploy AI solutions across Southeast Asia with confidence in their safety and compliance standards. > **Note:** For detailed integration guides and benchmark data for each SEA-Guard model, please refer to their individual documentation pages via the links above. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.sea-lion.ai/models/sea-guard.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.