# gpt-oss-safeguard-20b

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling.

Learn more about this model in OpenAI's gpt-oss-safeguard [user guide](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).

## Model Information

- **Organization**: [OpenAI](/llm.txt)
- **Slug**: gpt-oss-safeguard-20b
- **Available at Providers**: 10
- **Release Date**: October 29, 2025

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [Nano-GPT](/llm/nanogpt.txt) | GPT OSS Safeguard 20B |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | gpt-oss-safeguard-20b | 0.08 | 0.30 |  | [View](https://openrouter.ai/openai/gpt-oss-safeguard-20b) |
| [ValorGPT](/llm/valorgpt.txt) | gpt-oss-safeguard-20b |  |  |  | [View](https://www.valorgpt.com/models/openai-gpt-oss-safeguard-20b) |
| [Vercel AI Gateway](/llm/vercel.txt) | gpt-oss-safeguard-20b | 0.08 | 0.30 |  |  |
| [Yupp](/llm/yupp.txt) | gpt-oss-safeguard-20b (OpenRouter) |  |  |  |  |
| [LangDB](/llm/langdb.txt) | gpt-oss-safeguard-20b |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | OpenAI: gpt-oss-safeguard-20b | 0.08 | 0.30 |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/openai/gpt-oss-safeguard-20b |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | gpt-oss-safeguard-20b | 0.08 | 0.33 |  |  |
| [Writingmate](/llm/writingmate.txt) | OpenAI: gpt-oss-safeguard-20b |  |  |  | [View](https://writingmate.ai/models/openai/gpt-oss-safeguard-20b) |

---

[← Back to all providers](/llm.txt)