gpt-oss-safeguard-20b
OpenAI · openai/gpt-oss-safeguard-20b
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...
gpt-oss-safeguard-20b ranks #63 of 377 models in the default AI Benchmark Hub order (quality first, then cost). At $0.19 blended per million tokens, it is cheaper than 83% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 65536
Pricing
Output / 1M: 0.30
Blend / 1M: 0.19
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.19per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.19 |
| 10,000,000 | $1.88 |
| 100,000,000 | $18.75 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from OpenAI
- gpt-oss-120b$0.05 / 1M
- gpt-oss-20b$0.08 / 1M
- GPT-5 Nano$0.22 / 1M
- GPT-4.1 Nano$0.25 / 1M
- GPT-6 Luna Pro$0.30 / 1M
Closest API price
- MiniMax M3.1 Flash$0.19 / 1M
- Seed 1.6 Flash$0.19 / 1M
- Hy-MT2-30B-A3B$0.18 / 1M
- Hy-MT2-7B$0.18 / 1M
- Llama 3.2 3B Instruct$0.19 / 1M