OpenAI
gpt-oss-safeguard-20b
Released 2025-10-29
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...
You send / 1M
$0.075
tokens in
It replies / 1M
$0.300
tokens out
Memory
131K
tokens it can read at once
Typical request
$0.0002
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Groq | $0.075 | $0.300 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 66K tokens
- Repeated text is billed at $0.037 per 1M (prompt caching)
Similar models
- Step 3.5 FlashStepfun · $0.100 in / $0.300 out per 1M
- DeepSeek V4 Flash 0423DeepSeek · $0.140 in / $0.280 out per 1M
- Qwen3 32BQwen · $0.080 in / $0.280 out per 1M
- Mercury 3Inception · $0.100 in / $0.350 out per 1M
- Granite 4.2 8BIbm Granite · $0.060 in / $0.250 out per 1M
- Nemotron 3 Nano 30B A3BNVIDIA · $0.060 in / $0.240 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Reasoning AI ModelsTop No-Training Cheap Tool-Calling AI Models