OpenAI / openai/gpt-oss-safeguard-20b

GPT-OSS Safeguard 20B - access through LLMTR

GPT-OSS Safeguard 20B is OpenAI's open-weight safety model, trained to judge whether a piece of text complies with a policy you supply and to explain its reasoning. It suits content moderation, rule checking and classification flows, and works for general chat and coding help too. It reasons by default and returns that chain separately in the response. You can set the depth with `reasoning_effort` as `low`, `medium` or `high` - all three levels have a measured effect on this model. The `none` level is not accepted here. It supports tool/function calling and schema-enforced JSON output. It offers a 131K context window and produces at most 65,536 tokens per response. It accepts text only. It is offered free with a daily usage quota.

Technical specifications

Canonical IDopenai/gpt-oss-safeguard-20b
ProviderOpenAI
Context window131,072 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENSNot available
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENSNot available

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-oss-safeguard-20b","messages":[{"role":"user","content":"Hello"}]}'

Related models