GPT OSS Safeguard 20B pricing & specs
OpenAI · released 2025-10-29 · ● verified 2026-11-06
GPT OSS Safeguard 20B is an OpenAI model released on 2025-10-29. At $0.07 per million input tokens and $0.20 per million output tokens, its blended price of $0.1025 per 1M tokens is lower than 90% of the 185 models we track. It offers text input, a 128K-token context window, built-in reasoning, tool calling and structured output. Its weights are open, and it is available from 2 tracked hosting providers.
Ranked #3 of 20 in Cheapest GPT (OpenAI) Models, #7 of 20 in Cheapest Reasoning Models, #10 of 20 in Cheapest Claude Alternatives and #10 of 20 in Cheapest Models With Tool Calling.
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs GPT OSS Safeguard 20B |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −51.2% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −46.3% |
| GPT OSS 20B | $0.03 | $0.14 | 131.1K | −43.9% |
| GPT OSS 120B | $0.037 | $0.17 | 131.1K | −31.4% |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | 1.05M | −12.2% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Amazon Bedrock | $0.07 | $0.20 |
| Groq | $0.075 | $0.30 |
// embed this price badge
Show the live price of GPT OSS Safeguard 20B in your README or docs (updated daily):
[](https://aisignals.dev/models/openai/gpt-oss-safeguard-20b)
// faq
How much does GPT OSS Safeguard 20B cost?
GPT OSS Safeguard 20B costs $0.07 per million input tokens and $0.20 per million output tokens (cheapest tracked host: Amazon Bedrock). At 50M input and 10M output tokens per month that is about $5.50.
What is the context window of GPT OSS Safeguard 20B?
128K tokens, with up to 16.4K output tokens per request.
What are cheaper alternatives to GPT OSS Safeguard 20B?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), GPT OSS 20B ($0.03 in / $0.14 out) offer the same input types and capabilities for less.
Is GPT OSS Safeguard 20B open weights?
Yes. It is available from 2 tracked hosts; the cheapest is Amazon Bedrock at $0.07 input and $0.20 output per million tokens.
// spec sheet
- input / 1M
- $0.07
- output / 1M
- $0.20
- blended (3:1)
- $0.1025
- context
- 128K
- max output
- 16.4K
- input types
- text
- reasoning
- yes
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- Amazon Bedrock
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| GPT OSS 20B | $0.03 | $0.14 | $2.90 |
| GPT OSS Safeguard 20B | $0.07 | $0.20 | $5.50 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.