openai Open weights Reasoning

gpt-oss-safeguard-20b pricing & benchmarks

Released Oct 29, 2025 · served by 1 provider

Input / 1M tokens$0.075
Output / 1M tokens$0.300
Context window131K
Cached input$0.037
1M in + 300K out$0.17

What gpt-oss-safeguard-20b is

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...

Providers and prices for gpt-oss-safeguard-20b

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Groqcheapest $0.075 $0.300 131K 100.0%

FAQ

How much does the gpt-oss-safeguard-20b API cost?

$0.075 per 1M input tokens and $0.300 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.17.

Is gpt-oss-safeguard-20b free?

No. It is a paid model starting at $0.075 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for gpt-oss-safeguard-20b?

Groq at $0.075 input / $0.300 output per 1M tokens.

Can I self-host gpt-oss-safeguard-20b?

Yes — weights are published as openai/gpt-oss-safeguard-20b on Hugging Face, so you can run it on your own hardware.