Moderation and safetyMath and reasoning

gpt-oss-safeguard

Moderation by your own rules: you write the policy in plain text, and the model reasons and gives a decision with an explanation. Built on gpt-oss.

Developer
OpenAI, USA
First release
Oct 2025
Latest release
Oct 2025
Sizes
20B – 120B
License
Commercial use allowedApache 2.0
Russian
Not stated
Ready-made builds
GGUF, MLX (Apple)
Running
Available in OllamaNeeds a GPU
Industries
Security, Customer support
Deploy on your server Hugging Face

What it does

  • Moderation by internal company rules
  • Labeling disputed messages with an explanation
  • Checking reviews and listings before publishing

Where it is used

Marketplaces and classifiedsCommunity moderationChatbots

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. gpt-oss-safeguard 20B и 120B

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can gpt-oss-safeguard be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does gpt-oss-safeguard need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does gpt-oss-safeguard support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download gpt-oss-safeguard and what does it cost?

The gpt-oss-safeguard weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Textgpt-ossOpenAI · USACommercial use allowed

OpenAI's first open models since GPT-2. Reasoning and tool calling; the smaller version fits on a single GPU.

DetailsModeration and safetyGranite GuardianIBM · USACommercial use allowed

IBM judge models: they catch harm, profanity and jailbreak attempts, and in RAG and agents check whether an answer is grounded in the documents. You can state your own rule in words.

DetailsModeration and safetyQwen3GuardAlibaba (Qwen) · ChinaCommercial use allowed

Safety filters for 119 languages, Russian among them. The Stream version checks a bot's reply while it is being generated and can cut it off on the fly.

Details

Source: huggingface.co/openai/gpt-oss-safeguard-120b. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.