GPT OSS Safeguard 120B pricing & specs

OpenAI · released 2025-10-29 · ● verified 2026-10-11

input / 1M$0.15via Amazon Bedrock
output / 1M$0.60via Amazon Bedrock
context128K
max output16.4K

// price history ($/1M tokens)

$0.69
input $/1Moutput $/1M2025-10-29 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs GPT OSS Safeguard 120B
Gemma 4 E2B IT$0.04$0.08131.1K−81%
Qwen3.7 Flash$0.03$0.131M−79%
Qwen Turbo$0.05$0.201M−66.7%
DeepSeek V4 Flash 0731$0.06$0.181.05M−65.7%
GPT OSS 120B$0.05$0.25131.1K−61.9%
GPT OSS Safeguard 120B vs Qwen3.6 Flash →GPT OSS Safeguard 120B vs Qwen3.8 Flash →GPT OSS Safeguard 120B vs Qwen3.8 Omni Flash →Claude Haiku 5.5 vs GPT OSS Safeguard 120B →DeepSeek-V3.1 vs GPT OSS Safeguard 120B →Gemma 4 26B A4B IT vs GPT OSS Safeguard 120B →

// price by host

hostin $/1Mout $/1M
Amazon Bedrock$0.15$0.60

// faq

How much does GPT OSS Safeguard 120B cost?

GPT OSS Safeguard 120B costs $0.15 per million input tokens and $0.60 per million output tokens (cheapest tracked host: Amazon Bedrock). At 50M input and 10M output tokens per month that is about $13.50.

What is the context window of GPT OSS Safeguard 120B?

128K tokens, with up to 16.4K output tokens per request.

What are cheaper alternatives to GPT OSS Safeguard 120B?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.

Is GPT OSS Safeguard 120B open weights?

Yes. It is available from 1 tracked hosts; the cheapest is Amazon Bedrock at $0.15 input and $0.60 output per million tokens.

// spec sheet

input / 1M
$0.15
output / 1M
$0.60
blended (3:1)
$0.2625
context
128K
max output
16.4K
input types
text
reasoning
yes
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
n/a
price source
Amazon Bedrock

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
Qwen Turbo$0.05$0.20$4.50
GPT OSS Safeguard 120B$0.15$0.60$13.50

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.