OpenAI logo

GPT OSS 20B Safeguard

Pricing & Specs API
Free REST API for prices, specs and benchmarks
GPT OSS 20B Safeguard is OpenAI's language model with a 131K context window and up to 66K output tokens, available from 5 providers, starting at $0.07 / 1M input and $0.2 / 1M output. A safety-focused open-weights language model with 21B total parameters and 3.6B active parameters, trained to interpret custom safety policies, label content, and provide transparent safety reasoning.
Specifications
Canonical IDopenai-gpt-oss-20b-safeguard
TypeLanguage
StatusActive
CreatorOpenAIOpenAI
Providers
Context Window131K tokens
Max Output66K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters20B
HuggingFace Likes212
HuggingFace Downloads (30d)55,275
HuggingFace Downloads (all-time)323,598
Release Date · 12 months ago

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardFlexFastBatch
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
openai.gpt-oss-safeguard-20b
$0.07$0.2N/A$0.03$0.1$0.12$0.35$0.03$0.1
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b
$0.5$0.5N/A——————
Groq logo
Groq
groq/openai/gpt-oss-safeguard-20b
$0.075$0.3$0.037——————
OpenRouter logo
OpenRouter
openai/gpt-oss-safeguard-20b
$0.075$0.3$0.0375——————
Vercel AI Gateway logo
Vercel AI Gateway
openai/gpt-oss-safeguard-20b
$0.07$0.2N/A——————

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host GPT OSS 20B Safeguard, ranked by cheapest on-demand price. The model needs about 48 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP10sAzureAMD Alveo U250 FPGA (64GB)64 GB$1.65/hr
Standard_NV32as_v4AzureAMD Radeon Instinct MI2564 GB$1.86/hr
g2-standard-24GCP2× nvidia-l448 GB$1.99/hr
7 more instances can run GPT OSS 20B Safeguard
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GPT OSS 120B Safeguard131K$0.150$0.600Available
GPT OSS 20B Safeguard131K$0.070$0.200Current
GPT OSS 120B131K$0.030$0.170Available
GPT OSS 20B131K$0.015$0.070Deprecated

Model IDs

accounts/fireworks/models/gpt-oss-safeguard-20b
bedrock_mantle/openai.gpt-oss-safeguard-20b
fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b
groq/openai/gpt-oss-safeguard-20b
openai-gpt-oss-20b-safeguard
openai.gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b
openrouter/openai/gpt-oss-safeguard-20b