gpt-oss-safeguard-20b pricing & benchmarks
Released Oct 29, 2025 · served by 1 provider
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...
- Model ID:
openai/gpt-oss-safeguard-20b - Modality: text->text
- Tool calling: supported · Structured output: supported
- Weights:
openai/gpt-oss-safeguard-20bon Hugging Face
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.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| 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.