← All models
Flash — fastest and cheapest, lighter reasoningCommercial API
gpt-oss-safeguard-20b Pricing
OpenAI · openai-gpt-oss-safeguard-20b
Input / 1M tokens
$0.075
Output / 1M tokens
$0.300
Context window
131,072 tokens
≈ 175 pages of text
Max output
65,536 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0002
1,000 requests / month$0.21/mo10,000 requests / month$2.10/mo100,000 requests / month$21.00/moEstimate your own workloadOpens the calculator with gpt-oss-safeguard-20b preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. The lines are flat because the price hasn't changed since then.
What it excels at
Supports long-context text processing up to 128k tokens with emphasis on safety filtering and moderation tasks.
The business tradeoff
20B scale limits complex reasoning depth; output token pricing is four times input, increasing cost for generation-heavy workloads.
Cheaper from OpenAI
Head-to-head
Vendor list rates, as of Jun 19, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.