# GPT OSS Safeguard 20B API Pricing

As of October 10, 2026, GPT OSS Safeguard 20B costs $0.07 per 1M input tokens and $0.20 per 1M output tokens from Amazon Bedrock, the lowest of 4 providers. It has a 128,000-token context window and returns up to 16,000 tokens per response.

- Page: https://models.litellm.ai/models/gpt-oss-safeguard-20b
- Lab: OpenAI
- LiteLLM model name: `openai.gpt-oss-safeguard-20b`
- Context window: 128,000 tokens
- Max output: 16,000 tokens
- Added to LiteLLM: December 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Amazon Bedrock | `openai.gpt-oss-safeguard-20b` | $0.07 | $0.20 | – | – | – | 128K |
| Amazon Bedrock Mantle | `bedrock_mantle/openai.gpt-oss-safeguard-20b` | $0.07 | $0.20 | – | – | – | 128K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b` | $0.50 | $0.50 | – | – | – | 128K |
| Groq | `groq/openai/gpt-oss-safeguard-20b` | $0.075 | $0.30 | $0.037 | – | – | 128K |

## Cost examples

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

- Amazon Bedrock: $0.24
- Amazon Bedrock Mantle: $0.24
- Groq: $0.30
- Fireworks AI: $1.25

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

- Amazon Bedrock: $0.74
- Amazon Bedrock Mantle: $0.74
- Groq: $0.81
- Fireworks AI: $5.10

## Features

Supported: Function calling, Structured output, Reasoning, Web search.
Not supported: Image input, Audio input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="openai.gpt-oss-safeguard-20b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT OSS Safeguard 20B cost?

GPT OSS Safeguard 20B costs $0.07 per 1M input tokens and $0.20 per 1M output tokens from Amazon Bedrock, the lowest of 4 providers.

### What is the context window of GPT OSS Safeguard 20B?

GPT OSS Safeguard 20B has a 128,000-token context window and returns up to 16,000 tokens per response.

### Which providers offer GPT OSS Safeguard 20B?

GPT OSS Safeguard 20B is available from 4 providers through LiteLLM: Amazon Bedrock, Amazon Bedrock Mantle, Fireworks AI and Groq. The lowest price is on Amazon Bedrock.

### How do I call GPT OSS Safeguard 20B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="openai.gpt-oss-safeguard-20b", 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 20B support?

GPT OSS Safeguard 20B supports function calling, structured output, reasoning and web search. It does not support image input and audio input.

### When did LiteLLM add GPT OSS Safeguard 20B?

GPT OSS Safeguard 20B was added to LiteLLM's model price file in December 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json