RentGPU RentGPU
寻找 GPU →
by OpenAI

OpenAI: gpt-oss-safeguard-20b.

text closed laptop+ 20B params 131K ctx
Cheapest input
$0.075/M
on OpenAI API
Cheapest output
$0.3/M
on OpenAI API
Hosted equiv.
~$0.11/hr
@ 100 tok/s on OpenAI API

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

Hosted API only

No self-host path — closed weights.

OpenAI: gpt-oss-safeguard-20b's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenAI API api direct $0.075 $0.3 Launch ↗
OpenRouter api aggregator $0.075 $0.3 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run OpenAI: gpt-oss-safeguard-20b?
OpenAI: gpt-oss-safeguard-20b is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access OpenAI: gpt-oss-safeguard-20b?
OpenAI: gpt-oss-safeguard-20b is available via OpenAI API, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run OpenAI: gpt-oss-safeguard-20b?
API pricing starts at $0.075/M input tokens and $0.3/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is OpenAI: gpt-oss-safeguard-20b open-source or proprietary?
OpenAI: gpt-oss-safeguard-20b is a proprietary model from OpenAI. Access is API-only — there are no public weights to download.