gpt-oss-safeguard-20b
by OpenAI · openai/gpt-oss-safeguard-20b · #41 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:35 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$0.075
per 1M tokens
Output
$0.30
per 1M tokens
Blended (3:1)
$0.131
3 input : 1 output
Cache read
$0.037
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for gpt-oss-safeguard-20b with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.131 | $0.00795 | — |
| 50% | $0.117 | $0.006075 | −24% |
| 90% | $0.106 | $0.004575 | −42% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000127 | $0.1275 |
| Document summary | 8,000 | 1,000 | $0.0009 | $0.9 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00285 | $2.85 |
| Long-context analysis | 150,000 | 5,000 | $0.0127 | $12.75 |
Specs
Context window
131K
tokens
Max output
66K
tokens
Input modalities
text
Tokenizer
GPT