openai
OpenAI: gpt-oss-safeguard-20b
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...
Context
131k tokens
Input / 1M tokens
$0.07
Output / 1M tokens
$0.30
Benchmark
—
Pricing
Input tokens$0.07 per 1M tokens
Output tokens$0.30 per 1M tokens
Cache read$0.04 per 1M tokens
Technical details
Model IDopenai/gpt-oss-safeguard-20b
Context window131k tokens
Input modalitiestext
Output modalitiestext
TokenizerGPT
Max output tokens65,536
Use with MegaBrain
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://getmegabrain.com/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'openai/gpt-oss-safeguard-20b',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use OpenAI: gpt-oss-safeguard-20b?
Get an API key and start making requests in minutes.
Get an API key