OpenAI: GPT OSS Safeguard 20B
gpt-oss-safeguard-20b
GPT OSS Safeguard 20B 输入 $0.0975/百万 token,输出 $0.390/百万 token,上下文 131K,通过兼容 OpenAI 的接口调用。
Gpt-oss-safeguard is a first open weight reasoning model specifically trained for safety classification tasks to help classify text content based on customizable policies. As a fine-tuned version of gpt-oss, gpt-oss-safeguard is designed to follow explicit written policies that you provide. This enables bring-your-own-policy Trust & Safety AI, where your own taxonomy, definitions, and thresholds guide classification decisions. Well crafted policies unlock gpt-oss-safeguard's reasoning capabilities, enabling it to handle nuanced content, explain borderline decisions, and adapt to contextual factors.
模态
文本 → 文本
输入 / 输出价
$0.0975 / $0.390 每 1M
上下文
131K · 最长输出 66K
能力
价格
按实际 token 计费,从余额中扣除。人民币按 1 美元 ≈ 7.2 元折算,仅供参考。
| 计费项 | 美元 / 1M token | 人民币参考 |
|---|---|---|
| 输入 | $0.0975 | ¥0.70 |
| 输出 | $0.390 | ¥2.81 |
| 缓存命中(输入) | $0.0244 | ¥0.18 |
试算
拖动滑块估算这个模型的花费。
- 单次
- $0.00060
- 每天
- $0.3023
- 每月(30 天)
- $9.07≈ ¥65
GPT OSS Safeguard 20B:输入 $0.0975/M · 输出 $0.39/M · 缓存命中 $0.0244/M
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-oss-safeguard-20b", "max_tokens": 800,
"messages": [{"role": "user", "content": "…"}]}'接入代码
兼容 OpenAI 接口。把 Base URL 换成 https://api.geniusrelaygpt.com/v1,模型名填 gpt-oss-safeguard-20b。
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-oss-safeguard-20b",
"stream": true,
"messages": [{"role": "user", "content": "你好"}]
}'支持的参数
常用 OpenAI 参数都可以直接传。
temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed常见问题
- GPT OSS Safeguard 20B 怎么计费?
- 输入 $0.0975、输出 $0.390 每百万 token,命中缓存的输入按 $0.0244 计。每次请求的扣费都能在控制台使用日志里查到。
- 上下文有多长?
- 131K token。长对话每一轮都会按全部输入 token 计费,注意控制历史长度。
- 支持流式输出吗?
- 支持。请求里加 "stream": true,返回 SSE,格式与 OpenAI 一致。