gpt-oss-safeguard-20b pricing
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 & safety labeling. Learn more about this model in OpenAI's gpt-oss-safeguard [user guide](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide). Live index: 3 priced offers. Best input $0.075 per million tokens from Groq. Best output $0.300 per million tokens from Groq.
Pricing across providers
Use this table to read gpt-oss-safeguard-20b list prices. We show 3 sources right now. Lowest input in the grid: Groq. The chart below the table helps when output prices are much higher than input prices.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
FA Fireworks AI | $0.500 | $0.500 | — | — |
G Groq | $0.075 | $0.300 | $0.037 | — |
O Openrouter | $0.075 | $0.300 | — | — |
Input vs output · per provider
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how gpt-oss-safeguard-20b cost scales with traffic.
Provider
0.050000¢ / req
0.025000¢ / req
Model specifications
These fields describe gpt-oss-safeguard-20b as we store it (source: OpenAI). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Oct 2025
- Primary provider
- OpenAI
- Model family
- N/A
Compare gpt-oss-safeguard-20b
Pick any other model from the 1616-model catalog to open a side-by-side breakdown — provider matrix, specs, and a calculator on the same workload.
Locked
Compare with
Pick a model on both sides.
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: 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 ...
Related models
Models close to gpt-oss-safeguard-20b by family, provider, and context window — each with live pricing in our catalog.