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…

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](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).

Specifications & capabilities

Input
text
Output
text
Context window · tokens
131072
Knowledge cutoff
2024-10
Published model ID
gpt-oss-safeguard-20b
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling
Description source ↗

Published prices

1–12 / 12

gpt-oss-safeguard-20b ↗

$0.05

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gpt-oss-safeguard-20b ↗

$0.13

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

openai/gpt-oss-safeguard-20b ↗

$0.07

Inference provider
vercelAIGatewayCatalog
Platform
bedrock
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
bedrock | openai/gpt-oss-safeguard-20b
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-oss-safeguard-20b ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
bedrock
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
bedrock | openai/gpt-oss-safeguard-20b
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-oss-safeguard-20b ↗

$0.04

Inference provider
vercelAIGatewayCatalog
Platform
groq
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
groq | openai/gpt-oss-safeguard-20b
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-oss-safeguard-20b ↗

$0.08

Inference provider
vercelAIGatewayCatalog
Platform
groq
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
groq | openai/gpt-oss-safeguard-20b
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-oss-safeguard-20b ↗

$0.30

Inference provider
vercelAIGatewayCatalog
Platform
groq
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
groq | openai/gpt-oss-safeguard-20b
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-oss-safeguard-20b ↗

$0.07

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-oss-safeguard-20b ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
varies_by_provider
true
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–5 / 5

gpt-oss-safeguard-20b ↗

source model id
gpt-oss-safeguard-20b
hosting
gateway
platforms
  • Cheaper Inference
context length
128000
max output tokens
16000
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • structuredOutputs
  • toolCalling

openai/gpt-oss-safeguard-20b ↗

source model id
HuggingFace/openai-gpt-oss-safeguard-20b@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    GPT OSS Safeguard 20B ↗

    source model id
    openai.gpt-oss-safeguard-20b
    hosting
    bedrock-managed
    platforms
    • Amazon Bedrock
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      GPT OSS Safeguard 20B ↗

      source model id
      openai/gpt-oss-safeguard-20b
      hosting
      vercel-gateway
      platforms
      • Vercel AI Gateway
      context length
      128000
      max output tokens
      16000
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities
      • promptCaching
      • reasoning
      • structuredOutputs
      • toolCalling

      openai/gpt-oss-safeguard-20b ↗

      source model id
      publishers/hf-openai/models/gpt-oss-safeguard-20b@001
      hosting
      vertex-self-deployed
      platforms
      • Google Cloud Vertex AI
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        Safety assessments

        1–1 / 1

        Foundation Model Transparency Index 2025 ↗

        35 / 100

        source id
        stanfordFMTI
        canonical model id
        openai/gpt-oss-safeguard-20b
        taxonomy
        transparency
        hazard category
        transparency
        hazard name
        Organization transparency
        policy area
        OpenAI
        assessment type
        organization-level disclosure
        metric
        disclosure_score
        result label
        35 / 100
        sample size
        100
        updated at
        2026-11-09T18:08:05.227Z

        Source specification observations

        1–5 / 5

        openRouter ↗

        field
        context_length
        value
        131072
        normalized value
        131072
        scope
        source-model
        source id
        openRouter
        confidence
        1

        vercelAIGatewayCatalog ↗

        field
        context_length
        value
        128000
        normalized value
        128000
        scope
        source-model
        source id
        vercelAIGatewayCatalog
        confidence
        1

        vercelAIGatewayCatalog ↗

        field
        knowledge_cutoff
        reported field
        knowledge_cutoff
        value
        2024-10
        normalized value
        2024-10
        precision
        month
        scope
        source-model
        source id
        vercelAIGatewayCatalog
        confidence
        1

        openRouter ↗

        field
        max_output_tokens
        value
        65536
        normalized value
        65536
        scope
        source-model
        source id
        openRouter
        confidence
        1

        vercelAIGatewayCatalog ↗

        field
        max_output_tokens
        value
        16000
        normalized value
        16000
        scope
        source-model
        source id
        vercelAIGatewayCatalog
        confidence
        1

        Original sources

        1–15 / 15

        Hugging Face · openai/gpt-oss-safeguard-20b ↗

        Google Cloud · Model page ↗

        Microsoft Foundry · Model page ↗

        OpenRouter · Model page ↗

        Vercel AI Gateway · Model page ↗

        Microsoft Foundry · Model documentation ↗

        api.cheaperinference.com · Source snapshot ↗

        Amazon Web Services · Model page ↗

        Amazon Bedrock · Model documentation ↗

        Amazon Web Services · Catalog ↗

        GitHub · Catalog ↗

        Google Cloud · Catalog ↗

        Microsoft Foundry · Catalog ↗

        OpenRouter · Catalog ↗

        Vercel AI Gateway · Catalog ↗

        Source links

        1–8 / 8

        Explore more models

        Models

        Loading
        EVIDENCE / COMPARISON

        Benchmarks

        Explore every benchmark

        Loading

        These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

        Install TensorTrace