Atlas / Models / OpenAI / OpenAI: gpt-oss-safeguard-20b

OpenAI: gpt-oss-safeguard-20b✓ Catalog verified

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 & safety labeling. Learn more about this model in OpenAI's gpt-oss-safeguard user guide.

Input price
$0.07 /1M
Output price
$0.30 /1M
Context
131K
Modalities
text
Released
Oct 29, 2025
Tool calling
✓ Yes
Atlas signal
87/100
01

Overview

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 & safety labeling. Learn more about this model in OpenAI's gpt-oss-safeguard user guide.

Access: available through the official OpenAI API. Context window: 131K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifieropenai/gpt-oss-safeguard-20b
ProviderOpenAI
Model typeText LLM
Context window131K catalog
Input modalitiestext
Output modalitiestext
ReleasedOct 29, 2025
TokenizerGPT
ModeratedNo
Architecture modalitytext->text
Supported parameters
include_reasoningmax_tokensreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": null,
  "temperature": null,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for openai/gpt-oss-safeguard-20b as published in the catalog.

$0.07
Input /1M
$0.30
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$7.5e-8$0.07 / 1MPer input token
Completion tokens$3e-7$0.30 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.1Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

OpenAI: gpt-oss-safeguard-20b
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
79signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call OpenAI: gpt-oss-safeguard-20b through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="openai/gpt-oss-safeguard-20b",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does OpenAI: gpt-oss-safeguard-20b cost?

$0.07 per 1M input tokens and $0.30 per 1M output tokens on the official OpenAI API.

What is the context window of OpenAI: gpt-oss-safeguard-20b?

OpenAI: gpt-oss-safeguard-20b supports up to 131K tokens of context.

Does OpenAI: gpt-oss-safeguard-20b support tool / function calling?

Yes, OpenAI: gpt-oss-safeguard-20b supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access OpenAI: gpt-oss-safeguard-20b?

Use the official OpenAI API with the model id `openai/gpt-oss-safeguard-20b`. See the Quick start section above for code examples.