Model Price Index
Updated 2026-07-14 · Changelog

GPT OSS Safeguard 20B

Groq

OpenAI's open-weight GPT OSS Safeguard 20B running on Groq's LPU hardware — a policy-reasoning model for content classification and safety moderation. Currently in preview.

$0.075

Input

$0.30

Output

per 1M tokens

Ratesper 1M tokens

Input$0.075
Output$0.30

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $10.50/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Specifications

API Model IDopenai/gpt-oss-safeguard-20b
Context Window128K tokens
Max Output8K tokens
Modalitiestext
Capabilitiesstreaming · json-mode · reasoning

More Groq Text / Chat Models

Llama 3.1 8B Instant · GPT OSS 20B · Llama 4 Scout · GPT OSS 120B · Llama 4 Maverick · Qwen3 32B · Llama 3.3 70B Versatile · Kimi K2 ·