OpenAI · Single modalityReleased 2025-12-02

gpt-oss-safeguard-120b

openai/gpt-oss-safeguard-120b id

GPT OSS Safeguard 120B is OpenAI’s open-weight safety model for content moderation and guardrail enforcement. It helps teams evaluate content against custom safety policies and build scalable, adaptable protections for production AI applications.

ReasoningTool useStructured output

Type

Use gpt-oss-safeguard-120b

# Drop-in OpenAI-compatible client
$ import { generateText } from 'ai'
$ 
$ const { text } = await generateText({
$   model: 'openai/gpt-oss-safeguard-120b',
$   baseURL: 'https://synapse.garden/api/v1',
$   apiKey: process.env.MG_KEY,
$   prompt: 'Why is the sky blue?',
$ })

128K

CONTEXT WINDOW

16K

MAX OUTPUT

$0.165/M

INPUT · PER M

$0.660/M

OUTPUT · PER M

PRICING

List prices, every modality.

Rate	Per million tokens · USD
Input	$0.165/M
Output	$0.660/M

Honest list pricesHow we calculate prices

Other OpenAI models

See all 82

Model

Input

Output

Context

Type

gpt-6-lunaGPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.TOOLSREASONINGJSONWEB
Input
$0.110/M
Output
$0.550/M
Context
1.1M
gpt-6-luna-fastGPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.TOOLSREASONINGJSONWEB
Input
$0.220/M
Output
$1.10/M
Context
1.1M
gpt-6-solGPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools make it suited to software development and multi-step automation.TOOLSREASONINGJSONWEB
Input
$2.20/M
Output
$11.00/M
Context
1.1M
gpt-6-sol-fastGPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools make it suited to software development and multi-step automation.TOOLSREASONINGJSONWEB
Input
$4.40/M
Output
$22.00/M
Context
1.1M
gpt-live-1Our premier model for natural, expressive voice conversations with smooth interruption handling.
Input
—
Output
—
Context
—
gpt-image-2.5-flareGPT Image 2.5 Flare generates images from text and image inputs, optimized for fast, high-quality everyday image generation.TOOLS
Input
$5.50/M
Output
$33.00/M
Context
—
gpt-image-2.5-sunburstGPT Image 2.5 Sunburst generates and edits images from text and image inputs, with a focus on precise editing.TOOLS
Input
$5.50/M
Output
$33.00/M
Context
—
gpt-6-astraGPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.TOOLSREASONINGWEBJSON
Input
$11.00/M
Output
$55.00/M
Context
1.1M
gpt-6-astra-fastGPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.TOOLSREASONINGWEBJSON
Input
$22.00/M
Output
$110.00/M
Context
1.1M
gpt-5.6-lunaGPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost in the series.REASONINGTOOLSWEBJSON
Input
$0.220/M
Output
$1.32/M
Context
1.1M
gpt-5.6-luna-fastGPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost in the series.REASONINGTOOLSWEBJSON
Input
$0.440/M
Output
$2.64/M
Context
1.1M
gpt-5.6-solGPT-5.6 Sol is the flagship of OpenAI's GPT-5.6 series, its most capable model for long-horizon agentic work across coding, biology, and cybersecurity.REASONINGTOOLSWEBJSON
Input
$4.40/M
Output
$22.00/M
Context
1.1M

FAQ · GPT-OSS-SAFEGUARD-120B

Frequently asked

01 / 04

How do I call gpt-oss-safeguard-120b from my code?

Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘openai/gpt-oss-safeguard-120b’ and supply your Synapse Garden API key. No code changes beyond the base URL.

02 / 04

How much does gpt-oss-safeguard-120b cost?

Input: $0.165/M per million tokens. Output: $0.660/M per million tokens. The free tier includes a million tokens every month at no cost.

03 / 04

What's the context window for gpt-oss-safeguard-120b?

gpt-oss-safeguard-120b supports a context window of 128K tokens, with a maximum output of 16K tokens.

04 / 04

Do I need a separate Anthropic or OpenAI account?

No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.

READY

Try gpt-oss-safeguard-120b in three minutes.

Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.

Start free Quickstart