Skip to content
  • Models
  • Rankings
  • Ori
ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026. See ElevenLabs models

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for openai

OpenAI: gpt-oss-safeguard-20b

openai/gpt-oss-safeguard-20b

Model weights
Compare

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling.

Learn more about this model in OpenAI's gpt-oss-safeguard user guideOpens in new tab.

Modalities
In / Out Price
$0.075 / $0.30per 1M
Context
131K
Released
Oct 29, 2025
Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
$0.075$0.30$0.03750.32s641 tps
99.71%
Throughput
641tok/s

P50, best across providers

Latency
0.32s

P50, best provider

1.
Favicon for https://www.isekai.world/
ISEKAI ZERO
AI adventures. Travel with your favorite characters
9.14Btokens
2.
Favicon for https://github.com/FRAME-XYZ/equals-trust-and-safety
bots-moderation-hub
new
673Mtokens
3.
Favicon for https://rochat.ai/
Rochat AI
new
196Mtokens
4.
Favicon for https://ai.eastman.com/
Eastman AI Gateway Content Safety
new
139Mtokens
5.
Favicon for https://nekotina.com/
Nekotina
Encourage activity in your Discord server
120Mtokens

Frequently asked questions

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling. Learn more about this model in OpenAI's gpt-oss-safeguard user guide.

gpt-oss-safeguard-20b costs $0.075/M input tokens and $0.30/M output tokens, with separate rates for Cache Read at $0.0375/M tokens.

gpt-oss-safeguard-20b has a 131,072 token context window. It supports up to 65,536 completion tokens.

Yes. gpt-oss-safeguard-20b accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

GPT-6 Luna Decisions, GPT-6.1 Sol Pro, GPT-6.1 Sol and 62 more are other text models from OpenAI.

gpt-oss-safeguard-20b was released on October 29, 2025.