You're looking at a specific version of this model. Jump to the model overview.

lucataco /gpt-oss-safeguard-20b:e1ca36dc

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
reasoning_effort
None
medium
Reasoning effort level: 'low' for faster responses on straightforward cases, 'medium' for balanced reasoning (default), or 'high' for deeper analysis of complex edge cases
top_p
number
1

Max: 1

Nucleus sampling top-p
policy
string
Safety policy or rules to evaluate the prompt against. This defines the criteria for classification.
prompt
string
Your bank details are needed to complete this transaction.
Input prompt or question to evaluate
temperature
number
1

Max: 2

Sampling temperature (0 for greedy decoding)
max_new_tokens
integer
512

Min: 1

Max: 8192

Maximum number of tokens to generate
repetition_penalty
number
1

Min: 0.8

Max: 2

Repetition penalty to reduce repetitive text (1.0 = no penalty)

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'additionalProperties': True, 'title': 'Output', 'type': 'object'}