Skip to main content

gpt-oss-safeguard-20b

General purposeTools

OpenAI · Released October 2025

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...

It is part of OpenAI's GPT family, where Sol, Luna and Terra mark the current generation's capability tiers and Pro servings trade speed for deeper computation.

Facts and pricing

Provider
OpenAI
Context window
131K tokens
Input price
0.83 credits / 1M tokens ($0.075 raw)
Output price
3.3 credits / 1M tokens ($0.30 raw)
Vision (image input)
No
Tool calling
Yes
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

What gpt-oss-safeguard-20b is best for

Example prompts

Prompts that suit a general purpose model like gpt-oss-safeguard-20b:

OpenAI family

ModelContextInput cr/MOutput cr/MReleased
GPT-6 Astra1.1M110550September 2026
GPT-6 Astra Pro1.1M110550September 2026
GPT-5.6 Luna Pro1.1M2.213.2July 2026
GPT-5.6 Luna Pro (batch)1.1M1.16.6July 2026
GPT-5.6 Luna (batch)1.1M1.16.6July 2026
GPT-5.6 Luna1.1M2.213.2July 2026
GPT-5.6 Terra Pro (batch)1.1M11.066.0July 2026
GPT-5.6 Terra Pro1.1M22.0132July 2026
GPT-5.6 Terra1.1M22.0132July 2026
GPT-5.6 Terra (batch)1.1M11.066.0July 2026

All 90 OpenAI models

Frequently asked questions

What is gpt-oss-safeguard-20b?
gpt-oss-safeguard-20b is an AI model by OpenAI. 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...
How much does gpt-oss-safeguard-20b cost on Zeplik?
Input tokens cost 0.83 credits per million and output tokens 3.3 credits per million (1 credit = $0.10; the raw provider rates are $0.075 and $0.30 per million). New accounts start with free credits.
How long can a conversation with gpt-oss-safeguard-20b be?
gpt-oss-safeguard-20b has a 131K-token context window (131,072 tokens), which covers the conversation plus any documents you attach.
Does gpt-oss-safeguard-20b support images and tools?
gpt-oss-safeguard-20b is text-only and supports tool calling.

Related models

GPT-6 AstraFrontier

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...

1.1M ctx550 cr/M outSeptember 2026
GPT-6 Astra ProFrontier

GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx550 cr/M outSeptember 2026
GPT-5.6 Luna ProGeneral purpose

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx13.2 cr/M outJuly 2026
GPT-5.6 Luna Pro (batch)General purpose

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx6.6 cr/M outJuly 2026
GPT-5.6 Luna (batch)General purpose

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx6.6 cr/M outJuly 2026
GPT-5.6 LunaGeneral purpose

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx13.2 cr/M outJuly 2026

More you can do with gpt-oss-safeguard-20b

gpt-oss-safeguard-20b - OpenAI AI Model | Zeplik Chat