Skip to content
LLMs
OpenAI logo

OpenAI: gpt-oss-safeguard-20b

by OpenAI

OpenAI: gpt-oss-safeguard-20b is a large language model from OpenAI. It costs $0.075 per million input tokens and $0.300 per million output tokens. Its context window is 131K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights
Input / 1M tokens
$0.075
Output / 1M tokens
$0.300
Cached input / 1M
$0.037

On repeated prefixes

Context window
131K

tokens

Who serves it cheapest

1 hosts serve gpt-oss-safeguard-20b. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: gpt-oss-safeguard-20b, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
GroqCheapest$0.075$0.300131K-100.0%

About 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...

Specifications

OpenAI: gpt-oss-safeguard-20b specifications
Model IDopenai/gpt-oss-safeguard-20b
ProviderOpenAI
Context window131K tokens
Max output66K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - openai/gpt-oss-safeguard-20b
ReleasedOctober 29, 2025

Cheaper alternatives

Models that cost less than gpt-oss-safeguard-20b while keeping at least half its context window and every input modality it supports.

Frequently asked

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

$0.075 per million input tokens and $0.300 per million output tokens. Cached input reads cost $0.037 per million tokens.

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

131K tokens, with up to 66K tokens of output per request.

Confirm against the source: OpenAI official pricing.