Models / OpenAI
gpt-oss-safeguard-20b
by OpenAI ·
openai/gpt-oss-safeguard-20bgpt-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...
reasoningtool-usereleased 2025-10-29
Legal score · raw
-
not yet benchmarked
Context
131K
max output 66K
Input
$0.09
per 1M tokens
Output
$0.38
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.05
2.0x cheaper than uncached
Uncached input
$0.09
per 1M tokens
Capabilities
Modalities
in text
out text
Request parameters it accepts
include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.