---
title: "GPT OSS Safeguard 20B API pricing: 3 providers compared"
description: "GPT OSS Safeguard 20B API price per token from 3 providers: lowest listed USD 0.07 input and USD 0.20 output per 1M tokens. Source linked per row."
url: https://broadrouter.com/llm-api-pricing/gpt-oss-safeguard-20b/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# GPT OSS Safeguard 20B API pricing

Updated 2026-11-15

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for GPT OSS Safeguard 20B is Amazon Bedrock at USD 0.07 per 1M input tokens and USD 0.20 per 1M output tokens. The median across 3 standard prices is USD 0.075 / USD 0.30. Each price is read from the provider's own pricing page.

OpenAI · slug `gpt-oss-safeguard-20b` · up to 131,072 tokens of context · 3 providers with a standard price. **Every price is read from the provider's own pricing page** and linked in its row, checked 2026-11-15. No aggregator feed. [Download all prices](https://broadrouter.com/data/llm-api-provider-prices/) (every provider and model, with sources, CSV or JSON). How it compares with the market: the [LLM API price index](https://broadrouter.com/data/llm-api-price-index/). Archived list prices since 2025-11-06 (10 archived price points, 0 list-price changes): [LLM API price history](https://broadrouter.com/data/llm-api-price-history/#p-groq).

## Does OpenAI sell GPT OSS Safeguard 20B directly?

OpenAI publishes no price for GPT OSS Safeguard 20B on its own API that we could find, so this page compares hosts only.

## GPT OSS Safeguard 20B model facts

Facts from OpenAI's model card for [`openai/gpt-oss-safeguard-20b`](https://huggingface.co/openai/gpt-oss-safeguard-20b) and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

GPT OSS Safeguard 20B: facts as stated by the model card and the Hugging Face model API, with sources
| Fact | As stated | Source |
| --- | --- | --- |
| Open weights | Yes. The weights are in a public Hugging Face repository (openai/gpt-oss-safeguard-20b) with no access gate. | [Hugging Face model API](https://huggingface.co/api/models/openai/gpt-oss-safeguard-20b), checked 2026-11-16 · Quote: “"private": false, "gated": false, 3 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | [OpenAI model card metadata](https://huggingface.co/openai/gpt-oss-safeguard-20b), checked 2026-11-16 · Quote: “license: apache-2.0” |
| Total parameters | 21B | [OpenAI model card](https://huggingface.co/openai/gpt-oss-safeguard-20b), checked 2026-11-16 · Quote: “gpt-oss-safeguard-20b (21B parameters with 3.6B active parameters)” |
| Active parameters per token | 3.6B | [OpenAI model card](https://huggingface.co/openai/gpt-oss-safeguard-20b), checked 2026-11-16 · Quote: “gpt-oss-safeguard-20b (21B parameters with 3.6B active parameters)” |
| Context length | Not found on OpenAI's model card when we read it; see the context column in the price table | checked 2026-11-16 |
| Input and output | Text in, text out (the card's task tag is text-generation) | [OpenAI model card metadata](https://huggingface.co/openai/gpt-oss-safeguard-20b), checked 2026-11-16 · Quote: “pipeline_tag: text-generation” |
| Tool calling | Not found on OpenAI's model card when we read it | checked 2026-11-16 |
| First published on Hugging Face (not necessarily the release date) | 2025-09-18 | [Hugging Face model API](https://huggingface.co/api/models/openai/gpt-oss-safeguard-20b), checked 2026-11-16 · Quote: “"createdAt": "2025-09-18T18:51:08.000Z"” |

## GPT OSS Safeguard 20B price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 28% above the cheapest.

GPT OSS Safeguard 20B API prices by provider
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **[Amazon Bedrock](https://broadrouter.com/llm-api-pricing/providers/amazon-bedrock/)** cheapest · Note: Table headed "Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)". Quote: “GPT OSS Safeguard 20B $ 0.07 $ 0.20” | USD 0.07 | not published | USD 0.20 | USD 0.1025 | not stated | not stated | [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| 2 | **[Featherless](https://broadrouter.com/llm-api-pricing/providers/featherless/)** · `openai/gpt-oss-safeguard-20b` · Note: Developer plan (per-token billing, from 50 USD a month in credits). No cached price published. Quote: “PRICING: INPUT $0.075 / OUTPUT $0.3” | USD 0.075 | not published | USD 0.30 | USD 0.1312 | 32,768 | FP8 | [Featherless page](https://featherless.ai/models/openai/gpt-oss-safeguard-20b) · checked 2026-11-15 · re-checked 2026-11-16 |
| 3 | **[Groq](https://broadrouter.com/llm-api-pricing/providers/groq/)** · `openai/gpt-oss-safeguard-20b` · Note: Preview model (evaluation use only per Groq). Quote: “$0.075 input$0.30 output \| Cached Input $0.037” | USD 0.075 | USD 0.037 | USD 0.30 | USD 0.1312 | 131,072 | not stated | [Groq page](https://console.groq.com/docs/model/openai/gpt-oss-safeguard-20b) · checked 2026-11-14 · re-checked 2026-11-16 |

-   **Ranked:** standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
-   **Automated re-check 2026-11-16:** a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
-   **Precision** is shown only where the provider states it; "not stated" is unknown, not full precision.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20GPT%20OSS%20Safeguard%2020B%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fgpt-oss-safeguard-20b%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What does GPT OSS Safeguard 20B cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=gpt-oss-safeguard-20b). Providers without a cached price bill cached input at the input price.

-   **Support chatbot:** 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
-   **RAG over documents:** 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
-   **Coding agent (one developer):** 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.

Monthly cost of three workloads on GPT OSS Safeguard 20B, by provider
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
| --- | --- | --- | --- |
| **Amazon Bedrock** | USD 9.90 | USD 19.80 | USD 144.00 |
| **Featherless** | USD 12.15 | USD 22.50 | exceeds context |
| **Groq** | USD 10.10 | USD 19.76 | USD 103.86 |

For the support chatbot, the cheapest price (Amazon Bedrock, USD 9.90 a month) saves USD 0.2 against the median (USD 10.10). For the coding agent the gap is USD 40.14 a month (28% lower). The winner changes with the workload: Groq wins the cache-heavy agent, Amazon Bedrock the chatbot.

## Which GPT OSS Safeguard 20B provider is cheapest for your traffic?

Amazon Bedrock has the lowest input price (USD 0.07) and the lowest output price (USD 0.20), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

GPT OSS Safeguard 20B: price per 1M tokens at 3 input to 1 output, by share of input served from cache
| Provider | No cache hits | 50% cached | 90% cached |
| --- | --- | --- | --- |
| **Amazon Bedrock** (no cache price) | USD 0.1025 cheapest | USD 0.1025 cheapest | USD 0.1025 cheapest |
| **Featherless** (no cache price) | USD 0.1312 | USD 0.1312 | USD 0.1312 |
| **Groq** | USD 0.1312 | USD 0.117 | USD 0.1056 |

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

1 of 3 providers publishes a cached-input price below the input price: Groq (51% off). Amazon Bedrock and Featherless publish none, so cached tokens there bill at the input price.

Context windows differ: 131,072 tokens at Groq; 32,768 tokens at Featherless. Amazon Bedrock does not state one. The cheapest row is not always the one that fits a long prompt.

## What does GPT OSS Safeguard 20B cost in other languages?

The same text needs a different number of tokens in each language. With the gpt-oss (o200k\_harmony) tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for GPT OSS Safeguard 20B:

| Content | Input per 1M characters | Cheapest provider |
| --- | --- | --- |
| English | USD 0.015 | Amazon Bedrock |
| Arabic MSA | USD 0.022 | Amazon Bedrock |
| Hindi | USD 0.023 | Amazon Bedrock |
| Chinese | USD 0.054 | Amazon Bedrock |
| Code | USD 0.018 | Amazon Bedrock |

From BroadRouter's [real cost by language dataset](https://broadrouter.com/data/real-cost-by-language/), which covers 15 languages and content types for every model we could match to a measured tokenizer.

## Estimate your own bill

-   [LLM API cost calculator with GPT OSS Safeguard 20B preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=gpt-oss-safeguard-20b): your traffic and cache rate, against any of 431 models.
-   [gpt-oss token counter](https://broadrouter.com/tools/gpt-oss-token-counter/): count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/): what a higher cache-hit rate saves.

## How does GPT OSS Safeguard 20B compare with other OpenAI models?

The OpenAI models whose cheapest standard price is closest to GPT OSS Safeguard 20B's (USD 0.1025 blended):

OpenAI models priced closest to GPT OSS Safeguard 20B
| Model | Cheapest input | Cheapest output | Max context | Providers |
| --- | --- | --- | --- | --- |
| [GPT-5 Nano](https://broadrouter.com/llm-api-pricing/gpt-5-nano/) | USD 0.05 | USD 0.40 | — | 3 |
| [OpenAI GPT OSS 120B](https://broadrouter.com/llm-api-pricing/gpt-oss-120b/) | USD 0.03 | USD 0.17 | 131,072 | 21 |
| [GPT-6 Luna](https://broadrouter.com/llm-api-pricing/gpt-6-luna/) | USD 0.10 | USD 0.50 | 1,050,000 | 6 |
| [GPT-4o mini](https://broadrouter.com/llm-api-pricing/gpt-4o-mini/) | USD 0.15 | USD 0.60 | — | 3 |
| [GPT OSS 20B](https://broadrouter.com/llm-api-pricing/gpt-oss-20b/) | USD 0.018 | USD 0.09 | 131,072 | 10 |
| [GPT-5.6 Luna](https://broadrouter.com/llm-api-pricing/gpt-5.6-luna/) | USD 0.20 | USD 1.20 | 1,050,000 | 6 |

Priced closest from other makers: [Gemma 3 27B](https://broadrouter.com/llm-api-pricing/gemma-3-27b-it/) (Google, USD 0.10) · [Ministral 3 3B](https://broadrouter.com/llm-api-pricing/ministral-3b-2512/) (Mistral AI, USD 0.10) · [Mistral Small 3.2 24B Instruct](https://broadrouter.com/llm-api-pricing/mistral-small-3.2-24b-instruct/) (Mistral AI, USD 0.1062).

[All 431 models: API prices compared](https://broadrouter.com/llm-api-pricing/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [LLM API price index (open data)](https://broadrouter.com/data/llm-api-price-index/) · [Download all prices (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### How much does the GPT OSS Safeguard 20B API cost per token?

From USD 0.07 per 1M input tokens (USD 0.00000007 per token) and USD 0.20 per 1M output tokens (USD 0.0000002 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 0.075 input and USD 0.30 output. Each price was read from the provider's own pricing page; the source is linked in its row.

### Which provider is cheapest for GPT OSS Safeguard 20B?

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Amazon Bedrock, ranked on a blend of 3 input tokens to 1 output token (USD 0.1025 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.

### Does OpenAI sell GPT OSS Safeguard 20B on its own API?

OpenAI publishes no price for GPT OSS Safeguard 20B on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Amazon Bedrock at USD 0.07 / USD 0.20 per 1M tokens.

### Does GPT OSS Safeguard 20B have cached input pricing?

1 of 3 standard prices includes one. The lowest is USD 0.037 per 1M at Groq. Providers without one bill cached input at the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

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

Up to 131,072 tokens. 1 standard price comes with less, down to 32,768 tokens (Featherless). Check the context column before you pick the cheapest row for long prompts. [Context window calculator](https://broadrouter.com/tools/context-window-calculator/).

### How much does a coding agent cost per month on GPT OSS Safeguard 20B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 103.86 a month at Groq, USD 144.00 at the median price and USD 162.00 at Featherless. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=gpt-oss-safeguard-20b).

### Is GPT OSS Safeguard 20B free to use through an API?

No provider in our data lists a free price for GPT OSS Safeguard 20B as of 2026-11-15. [Free tiers and credits by provider](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) lists general offers that do not name a model; [all free LLM API models](https://broadrouter.com/llm-api-pricing/free/) are on one page.

### Is GPT OSS Safeguard 20B open source, with open weights, and what is its licence?

OpenAI publishes the weights on Hugging Face as [`openai/gpt-oss-safeguard-20b`](https://huggingface.co/openai/gpt-oss-safeguard-20b), in a public repository with no access gate. The licence, as the [OpenAI model card metadata](https://huggingface.co/openai/gpt-oss-safeguard-20b) states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from OpenAI's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

### How many parameters does GPT OSS Safeguard 20B have?

Total parameters, as the [OpenAI model card](https://huggingface.co/openai/gpt-oss-safeguard-20b) states them: 21B. Active parameters per token: 3.6B. (checked 2026-11-16; BroadNet did not verify these figures.)

### How do I call GPT OSS Safeguard 20B with the OpenAI SDK?

BroadNet does not serve GPT OSS Safeguard 20B. Use the OpenAI-compatible base URL of a provider that lists it: create the client with `OpenAI(base_url=..., api_key=...)` and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: [Groq](https://broadrouter.com/llm-api-pricing/providers/groq/) (`https://api.groq.com/openai/v1`, model `openai/gpt-oss-safeguard-20b`). Each provider page quotes the provider's docs with a check date.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-gpt-oss-safeguard-20b&utm_content=page-cta) ·

**Sources**

-   [Amazon Bedrock: pricing (checked 2026-11-14)](https://aws.amazon.com/bedrock/pricing/)
-   [Featherless: pricing (checked 2026-11-15)](https://featherless.ai/models/openai/gpt-oss-safeguard-20b)
-   [Groq: pricing (checked 2026-11-14)](https://console.groq.com/docs/model/openai/gpt-oss-safeguard-20b)
