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.

It is part of OpenAI's GPT family, where GPT-6 Astra leads, GPT-6 Sol and GPT-6 Luna cover the capability and speed tiers below it, the GPT-5.6 generation sits behind them, and Pro servings trade speed for deeper computation.

Facts and pricing

Provider
OpenAI
Context window
131K tokens
Input price
0.90 credits / 1M tokens ($0.075 raw)
Output price
3.6 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 1.20x 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-6.1 Terra Pro1.1M12.060.0October 2026
GPT-6.1 Terra1.1M12.060.0October 2026
GPT-6.1 Sol Pro1.1M24.0120September 2026
GPT-6.1 Sol1.1M24.0120September 2026
GPT-6 Luna Pro (batch)1.1M0.603.0September 2026
GPT-6 Luna Pro1.1M1.26.0September 2026
GPT-6 Luna1.1M1.26.0September 2026
GPT-6 Luna (batch)1.1M0.603.0September 2026
GPT-6 Sol Pro (batch)1.1M12.060.0September 2026
GPT-6 Sol Pro1.1M24.0120September 2026

All 71 OpenAI models

Model comparisons

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.
How much does gpt-oss-safeguard-20b cost on Zeplik?
Input tokens cost 0.90 credits per million and output tokens 3.6 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-6.1 Terra ProFrontier

GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.

1.1M ctx60.0 cr/M outOctober 2026
GPT-6.1 TerraFrontier

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.

1.1M ctx60.0 cr/M outOctober 2026
GPT-6.1 Sol ProFrontier

GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.

1.1M ctx120 cr/M outSeptember 2026
GPT-6.1 SolFrontier

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.

1.1M ctx120 cr/M outSeptember 2026
GPT-6 Luna Pro (batch)General purpose

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-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 ctx3.0 cr/M outSeptember 2026
GPT-6 Luna ProGeneral purpose

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-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 ctx6.0 cr/M outSeptember 2026

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