LiteLLMModels

GPT OSS Safeguard 120B API Pricing

As of October 10, 2026, GPT OSS Safeguard 120B costs $0.15 per 1M input tokens and $0.60 per 1M output tokens from Amazon Bedrock, the lowest of 3 providers. It has a 128,000-token context window and returns up to 16,000 tokens per response.

By OpenAIModel ID openai.gpt-oss-safeguard-120bPrices updated Checked
Input
$0.15 / 1M tokens
Output
$0.60 / 1M tokens
Context window
128,000 tokens
Max output
16,000 tokens
Providers
3
Added to LiteLLM
December 2025

GPT OSS Safeguard 120B pricing by provider

3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
Amazon Bedrockopenai.gpt-oss-safeguard-120b$0.15$0.60128K
Amazon Bedrock Mantlebedrock_mantle/openai.gpt-oss-safeguard-120b$0.15$0.60128K
Fireworks AIfireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b$1.20$1.20128K

Other GPT OSS Safeguard 120B prices on Amazon Bedrock

Flex input$0.07 per 1M tokens
Flex output$0.30 per 1M tokens

What GPT OSS Safeguard 120B costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Amazon Bedrock$0.60
Amazon Bedrock Mantle$0.60
Fireworks AI$3.00

100 long-document requests with 100,000 input and 2,000 output tokens each

Amazon Bedrock$1.62
Amazon Bedrock Mantle$1.62
Fireworks AI$12.24

GPT OSS Safeguard 120B features

Use GPT OSS Safeguard 120B with LiteLLM

Call GPT OSS Safeguard 120B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="openai.gpt-oss-safeguard-120b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: gpt-oss-safeguard-120b
    litellm_params:
      model: openai.gpt-oss-safeguard-120b
      aws_region_name: os.environ/AWS_REGION_NAME
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gpt-oss-safeguard-120b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GPT OSS Safeguard 120B FAQ

How much does GPT OSS Safeguard 120B cost?

GPT OSS Safeguard 120B costs $0.15 per 1M input tokens and $0.60 per 1M output tokens from Amazon Bedrock, the lowest of 3 providers.

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

GPT OSS Safeguard 120B has a 128,000-token context window and returns up to 16,000 tokens per response.

Which providers offer GPT OSS Safeguard 120B?

GPT OSS Safeguard 120B is available from 3 providers through LiteLLM: Amazon Bedrock, Amazon Bedrock Mantle and Fireworks AI. The lowest price is on Amazon Bedrock.

How do I call GPT OSS Safeguard 120B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="openai.gpt-oss-safeguard-120b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does GPT OSS Safeguard 120B support?

GPT OSS Safeguard 120B supports function calling, structured output and reasoning. It does not support image input and audio input.

When did LiteLLM add GPT OSS Safeguard 120B?

GPT OSS Safeguard 120B was added to LiteLLM's model price file in December 2025.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Amazon Bedrock, Fireworks AI.

Provider pages: Amazon Bedrock, Amazon Bedrock Mantle, Fireworks AI.