OpenAI: GPT OSS Safeguard 20B

Safety model for policy screening, moderation, and risk-aware routing workflows

Source-linked gpt-oss Open weights Released 2025-10-29

API record Report

InputT

OutputT

Input price$0.07/M

Output price$0.2/M

Context131.072K

Max output131.072K

Providers7

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering GPT OSS Safeguard 20B
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Amazon Bedrock	`openai.gpt-oss-safeguard-20b`	128K	16.384K	$0.07	$0.2	—	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`openai/gpt-oss-safeguard-20b`	128K	16K	$0.07	$0.2	—	ReasoningTools	Docs ↗
Merge Gateway	`openai/gpt-oss-safeguard-20b`	4.096K	4.096K	$0.07	$0.2	—	Reasoning	Docs ↗
OpenRouter	`openai/gpt-oss-safeguard-20b`	131.072K	65.536K	$0.075	$0.3	$0.037	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`openai/gpt-oss-safeguard-20b`	131.072K	65.536K	$0.075	$0.3	$0.037	ReasoningToolsJSON	Docs ↗
Groq	`openai/gpt-oss-safeguard-20b`	131.072K	65.536K	$0.075	$0.3	—	ReasoningToolsJSON	Docs ↗
NanoGPT	`openai/gpt-oss-safeguard-20b`	128K	16.384K	$0.075	$0.3	—	Reasoning	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.07/M

Across 7 priced providers

Median input $0.075/M

Midpoint of listed rates

Highest input $0.075/M

1.1× the lowest listed rate

Output range $0.2 – $0.3

Per million output tokens

Amazon Bedrock $0.07/M

Vercel AI Gateway $0.07/M

Merge Gateway $0.07/M

OpenRouter $0.075/M

Kilo Gateway $0.075/M

Groq $0.075/M

NanoGPT $0.075/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

3 providers list the identical $0.07 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 4.096K to 131.072K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

× Tool calling No

× Structured output No

× Attachments No

× Vision input No

✓ Open weights Yes

Creator: OpenAI
Model family: gpt-oss
Knowledge cutoff: Not documented
License: Not documented
Release date: 2025-10-29
Model ID: openai/gpt-oss-safeguard-20b

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Sep 11, 2026Max Output Tokens65536 → 131072

Sep 11, 2026Price Completion0.3 → 0.2

Sep 11, 2026Price Prompt0.075 → 0.07

Sep 11, 2026Max Output Tokens131072 → 65536

Sep 11, 2026Price Completion0.2 → 0.3

Sep 11, 2026Price Prompt0.07 → 0.075

Sep 11, 2026Max Output Tokens65536 → 131072

Sep 11, 2026Price Completion0.3 → 0.2

Sep 11, 2026Price Prompt0.075 → 0.07

Sep 11, 2026Max Output Tokens131072 → 65536

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Models.devcatalog ↗Amazon Bedrock documentationprovider documentation ↗Vercel AI Gateway documentationprovider documentation ↗Merge Gateway documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗Groq documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/openai/gpt-oss-safeguard-20b

curl

curl "https://model.kyssta.lol/api/v1/models/openai/gpt-oss-safeguard-20b"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is GPT OSS Safeguard 20B?

Safety model for policy screening, moderation, and risk-aware routing workflows. It is published by OpenAI and catalogued here from Models.dev.

How much does GPT OSS Safeguard 20B cost?

Listed input pricing starts at $0.07 per million tokens from Amazon Bedrock, rising to $0.075 across 7 listed providers.

What is the context length of GPT OSS Safeguard 20B?

GPT OSS Safeguard 20B accepts up to 131.072K tokens of context and returns up to 131.072K output tokens.

Does GPT OSS Safeguard 20B support tool calling and structured output?

Provider catalogs list support for reasoning.

Which providers serve GPT OSS Safeguard 20B?

7 providers list this model: Amazon Bedrock, Vercel AI Gateway, Merge Gateway, OpenRouter, Kilo Gateway, Groq and 1 more.

Are the weights for GPT OSS Safeguard 20B open?

Yes. The weights are published and downloadable from Hugging Face.

When was GPT OSS Safeguard 20B released?

The catalog records a release date of 2025-10-29, last verified Sep 11, 2026.

More models from OpenAI

View all →

OpenAI: GPT-5.3 Chat

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...

128K ctx $1.75/M in OpenAI: GPT-5.6 Luna Pro

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.05M ctx $0.2/M in OpenAI: GPT-5.6 Terra Pro

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.05M ctx $2/M in OpenAI: GPT-5.6 Sol Pro

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.05M ctx $2/M in