Tasks and inputs
GPT OSS Safeguard 20B is listed for Content Moderation. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 13, 2026
GPT OSS Safeguard 20B from OpenAI: Safety model for policy screening, moderation, and risk-aware routing workflows.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Safety model for policy screening, moderation, and risk-aware routing workflows. The registry places it in the gpt-oss family with a release date of 2025-10-29. This profile describes its documented interface and how to evaluate it for the intended task.
The recorded inputs are text, with text output. The registry lists a 131,072-token context window and up to 131,072 output tokens. It also declares reasoning, function calling and structured output. These are specifications, not a measured quality or speed ranking. A host can impose its own request limits and support a different subset of features.
The registry marks GPT OSS Safeguard 20B as an open-weight model. Check the linked checkpoint’s licence and runtime requirements before downloading or deploying it. Open weights describe availability, while licence terms determine permitted use. Local inference still requires hardware; a hosted route can charge separately.
No independently checked token rate is added from a hosting alias. Use the route’s current price and billing unit when comparing cost, including output, reasoning, cache behavior and retries where applicable.
Test harmful and harmless examples in the languages and formats your product receives. Inspect false positives as well as missed violations, retain the policy version, and decide what happens when the model is uncertain. A moderation label is an input to your policy workflow.
A supporting source document was retrieved for this entry. Specifications above remain attributed to the models.dev record unless the publisher supplies a more specific limit. SyncDev has not independently benchmarked GPT OSS Safeguard 20B.
Browse OpenAI models, explore related tasks, or compare two models using the same workload.
Compare the model on the work you need to complete.
GPT OSS Safeguard 20B is listed for Content Moderation. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 131.07K context and 131.07K maximum output. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
The weights are downloadable under the publisher’s model licence. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Mistral AI
Shieldstral 1.0 is a compact open-weight moderation model that classifies text and image inputs against natural-language policy questions.
OpenAI
GPT OSS Safeguard 120B from OpenAI: Safety model for policy screening, moderation, and risk-aware routing workflows.
Meta
Llama-Guard-3-8B from Meta: Llama 3.1-based safety classifier for moderating prompts and model responses.