Skip to content
OpenKey

gpt-oss-safeguard-20b

OpenAIReleased Oct 29, 2025

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...

Try in playground
Context window
131K tokens
Max output
66K tokens
Input
text
Output
text
Tokenizer
GPT
Released
Oct 29, 2025
Reasoning
always on

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.075$0.0022$0.077
Output$0.300$0.0090$0.309
Cache read$0.037$0.0011$0.039

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-oss-safeguard-20b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-safeguard-20b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="openai/gpt-oss-safeguard-20b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-oss-safeguard-20b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does gpt-oss-safeguard-20b cost via API?
Through OpenKey, gpt-oss-safeguard-20b costs $0.077 per 1M input tokens and $0.309 per 1M output tokens. That is the provider price ($0.075 / $0.300) plus a flat 3% fee — nothing else.
What is gpt-oss-safeguard-20b's context window?
gpt-oss-safeguard-20b accepts up to 131K tokens of context and returns up to 66K tokens per request.
Is gpt-oss-safeguard-20b OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-oss-safeguard-20b" using any OpenAI SDK — only the base URL and API key change.
What inputs does gpt-oss-safeguard-20b support?
gpt-oss-safeguard-20b accepts text input and produces text output.

More from OpenAI

All OpenAI models →