BazaarLinkBazaarLink
Sign in

OpenAI: GPT-OSS Safeguard 20B

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...

Input → Output
Input / Output price
From $0.07 / $0.20 per 1M
NT$ 2 / 7
Cache read / write
From $0.04 / — per 1M
NT$ 1 / —
Context
131K
Released
October 2025

Performance

The last 24 hours, all hosts combined. When one host fails, BazaarLink automatically routes to the next healthy one.

Availability
—
Loading…
Time to first token (TTFT)
—
Loading…
Throughput (TPS)
—
Loading…
Trend: last 24 hours, one point per hour; a gap means too few requests in that hour.

Hosts

Each host has its own price, and prices can differ between hosts. You can name a preferred host in your request.

2 hosts · customer prices per million tokensLatency / throughput
HostInput /MOutput /MCache read /MCache write /MFirst tokenThroughputAvailability (24h)
Amazon Bedrock
$0.07
$0.20
$0.04
—0.35s274 tps100.0%
Groq
$0.07
$0.30
$0.04
—0.33s579 tps100.0%
Prices are customer prices per million tokens.

Benchmarks

Artificial Analysis has not evaluated this model yet.

Price comparison

Input, output and cache usage of this model are all billed at BazaarLink's price.

BazaarLink price This site

Input$0.07NT$ 2
Output$0.30NT$ 10
Cache read$0.04NT$ 1
Cache write—
3:1 blend (estimate)$0.13NT$ 4
All unit prices are per 1M tokens. TWD credit cards and Taiwan e-invoices supported. USD/TWD = 32.78 · before tax

Quick start

Just change base_url to use GPT-OSS Safeguard 20B through the BazaarLink API.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.bazaarlink.ai/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

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

FAQ

What is 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...

How much does the GPT-OSS Safeguard 20B API cost?

GPT-OSS Safeguard 20B costs $0.07 per 1M input tokens and $0.30 per 1M output tokens when accessed through BazaarLink.

How do I use GPT-OSS Safeguard 20B with the OpenAI SDK?

Set base_url to "https://api.bazaarlink.ai/v1" and use model ID "openai/gpt-oss-safeguard-20b". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for GPT-OSS Safeguard 20B?

GPT-OSS Safeguard 20B supports a context window of 131,072 tokens.

Is GPT-OSS Safeguard 20B available for free?

GPT-OSS Safeguard 20B is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.

Explore

More OpenAI models
Why use GPT-OSS Safeguard 20B through BazaarLink?
  • Billed in USD with TWD quotes plus Taiwan e-invoices, so Taiwanese teams do not need an overseas card
  • OpenAI-compatible API, no code rewrite
  • When an upstream source has a problem, the request can try another available source; if none is available you get an error
  • Chinese-language support from a local team
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.