Skip to content

Command Palette

Search for a command to run...

Model Explorer

OpenAI

gpt-oss-safeguard-20b

textOpen weightactive
Source
Context window
131,072
Maximum output
—
Catalog last checked
10/15/2026
Capabilities
include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Deployment
API via OpenRouter

Modalities

text

Current pricing

Effective rows only. When two sources disagree, both are shown and neither is picked for you.

input token

$0.08 / 1M tokens

Price unchanged since 9/25/2026, last confirmed 10/15/2026 per OpenRouter model catalog · not yet cross-checked against a second source

cached input token

$0.04 / 1M tokens

Price unchanged since 9/25/2026, last confirmed 10/15/2026 per OpenRouter model catalog · not yet cross-checked against a second source

output token

$0.30 / 1M tokens

Price unchanged since 9/25/2026, last confirmed 10/15/2026 per OpenRouter model catalog · not yet cross-checked against a second source

Where to use gpt-oss-safeguard-20b

9 providers in the catalog list this model. Resellers and gateways often charge a different price from the model maker; check their terms, rate limits and data policies as well as price.

ProviderInput / 1M tokensOutput / 1M tokens
OpenAIFirst-party(this page)$0.08$0.30
Amazon Bedrock$0.07$0.20
Merge Gateway$0.07$0.20
Vercel AI Gateway$0.07$0.20
Kilo Gateway$0.08$0.30
NanoGPT$0.08$0.30
Openrouter$0.08$0.30
LowRouter$0.08$0.24
AI/ML API$0.10$0.41