Skip to content

Model

GPT OSS Safeguard 120B

Safety model for policy screening, moderation, and risk-aware routing workflows

5 providers · 5 listingsreleased open weights
$0.15
lowest input /M · Vercel AI Gateway
$0.6
lowest output /M · Vercel AI Gateway
131K
context window
128K
max output

Compare providers (sorted by listed input price)

5 providers list GPT OSS Safeguard 120B. The cheapest full-context option is Vercel AI Gateway at $0.15/$0.6 per M.

5 listings
Cache read /MCache write /MCapabilitiesStatus
Vercel AI Gateway
openai/gpt-oss-safeguard-120b
$0.15$0.6128Kreasoningtoolsstructuredno visionOct 29, 2025
Amazon Bedrock
openai.gpt-oss-safeguard-120b
$0.15$0.6128Kreasoningtoolsstructuredno visionOct 29, 2025
Merge Gateway
openai/gpt-oss-safeguard-120b
$0.15$0.64Kreasoningno toolsno structuredno visionOct 29, 2025
Tinfoil
gpt-oss-safeguard-120b
$0.15$0.6131Kno reasoningtoolsstructuredno visionOct 29, 2025
Cortecs
gpt-oss-safeguard-120b
$0.179$0.697128Kreasoningtoolsstructuredno visionOct 29, 2025

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M
$0.15unchanged
Best output /M
$0.6unchanged
Provider coverage
5
4 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

Current price badge for GPT OSS Safeguard 120B
![GPT OSS Safeguard 120B price](https://www.vaanalytics.in/badge/openai/gpt-oss-safeguard-120b.svg)
https://www.vaanalytics.in/badge/openai/gpt-oss-safeguard-120b.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →
  • capabilityvia amazon-bedrock · Sep 13, 2026
    • reasoning: false → true
  • capabilityvia tinfoil · Sep 7, 2026
    • reasoning: true → false
  • capabilityvia amazon-bedrock · Aug 26, 2026
    • open_weights: false → true
  • new modelvia vercel · Aug 25, 2026

Weights

Permissiveapache-2.0120B params

Standard open-source terms. Commercial use without additional conditions. Weights download without an access request.

Derived from openai/gpt-oss-120b.

licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.