gpt-oss-safeguard-20b
OpenAIfamily · gpt-osshuggingface.co/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...
Updated 4 h ago · first seen 11 Sept 2026
model_01M294WW9KM7CQ555DQNXZEDRK
Overview
Identity
- Canonical model
- Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
- Official checkpoints
- official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
- Artifacts
- None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
- Provider deployments
- 3
- API aliases
- openai/gpt-oss-safeguard-20bIdentifiers under which providers and evaluators refer to this model.
- Folded evaluation variants
- 0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.
Openness
Open weights— weights downloadable under Apache-2.0; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.
Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.
Weights
Yes
Inference code
—
Training code
—
Training data
—
Dataset
—
Commercial use
Yes
Redistribution
Yes
Derivatives
Yes
Licence: Apache License 2.0 (permissive · SPDX Apache-2.0 · stated as “apache-2.0”)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 d agomedium
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Capabilities
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 5 d agomedium
Providers & Pricing3
All offers in the price terminal →USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →
Price history
Output price · USD / 1M tokens 3 providers
- OpenAI API
- GroqCloud
- OpenRouter
- OpenRouterfirst observed $0.3012 Sept 2026
- GroqCloudfirst observed $0.3011 Sept 2026
- OpenAI APIfirst observed $0.3011 Sept 2026
Input price · USD / 1M tokens 3 providers
- OpenAI API
- GroqCloud
- OpenRouter
- OpenRouterfirst observed $0.07512 Sept 2026
- GroqCloudfirst observed $0.07511 Sept 2026
- OpenAI APIfirst observed $0.07511 Sept 2026
Hardware fit37
Assumptions (7)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
- A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
- Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
- Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
- Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.
Lineage
Open in Graph →- ancestor: gpt-oss-20b
Versions & Artifacts0
Version history
Context windowfirst observation only
11 Sept 2026current
Licensefirst observation only
11 Sept 2026current
Max outputfirst observation only
11 Sept 2026current
Opennessfirst observation only
11 Sept 2026current
Parametersfirst observation only
11 Sept 2026current
Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.
Artifacts 0
No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.
Papers1
- arXiv:2508.10925Active35
Timeline3
Full timeline →OpenRouter lists gpt-oss-safeguard-20b at $0.075 in / $0.3 out per 1M tokens
openroutergpt-oss-safeguard-20b: release date changed from 2025-09-18 to 2025-10-29
Release date18 Sept 2025→29 Oct 2025openroutergpt-oss-safeguard-20b: release date changed from 2025-10-29 to 2025-09-18
Release date29 Oct 2025→18 Sept 2025huggingface
Change history59
Viewing AI Atlas as of 16 Mar 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →gpt-oss-safeguard-20b was not yet in AI Atlas on 16 Mar 2026
Release daterelease_date6
Opennessopenness1
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Context windowcontext_length1
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Tokenizertokenizer1
Base modelbase_model1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Model cardmodel_card_url1
Downloadsmetric.downloads6
Likesmetric.likes3
Accessaccess1
Commercial use allowedcommercial_use_allowed1
Derivatives allowedderivatives_allowed1
Descriptiondescription1
Gatedgated1
Groq model idgroq_model_id1
Groq statusgroq_status1
Hf inference providershf_inference_providers1
Last modifiedlast_modified1
Library namelibrary_name1
License keylicense_key1
License rawlicense_raw1
Downloads all timemetric.downloads_all_time6
Model typemodel_type1
Openrouter idopenrouter_id1
Openrouter listed atopenrouter_listed_at1
Reasoningreasoning1
Redistribution allowedredistribution_allowed1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Weights availableweights_available1
Weights dtypeweights_dtype1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
43
Source tiers
T1T22 / 41
Freshest observation
5 h ago
Conflicts
None
Source documents 5
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (73/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →