/ Models

Language models

OpenAI: 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...

Maker
Openai
Context window
131K
Max output
66K
Input / 1M
$0.075
Output / 1M
$0.3
1M in + 1M out
$0.375

Everything else

Max output66K
Input / 1M$0.075
Output / 1M$0.3
Cache read / 1M$0.037
Cache write / 1M
1M in + 1M out$0.375
Takestext
Returnstext
Toolsyes
Reasoningalways on
Open weightsyes
Released2025-10-29
Knowledge cutoff
Retires
Catalog idopenai/gpt-oss-safeguard-20b

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models