modelgrep
O

OpenAI: gpt-oss-safeguard-20b

openai/gpt-oss-safeguard-20b

Cheaper than 88% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
570
2nd fastest
Latency
229ms
first token
Input price
$0.075
35th cheapest
Context
131K
66K max out

How it compares

Faster than99%
of all ranked models
Cheaper than88%
of all ranked models

Overview

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...

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Groq$0.075$0.300100%

Specifications

Context window131K
Max output66K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.037/M
ModeratedNo

gpt-oss-safeguard-20b FAQ

How much does gpt-oss-safeguard-20b cost?

gpt-oss-safeguard-20b costs $0.075 per million input tokens and $0.300 per million output tokens via OpenRouter, making it 35th cheapest of 298 paid models.

How fast is gpt-oss-safeguard-20b?

gpt-oss-safeguard-20b generates around 570 tokens per second with 229ms time-to-first-token (p50), the 2nd fastest tracked model.

What is gpt-oss-safeguard-20b's context window?

gpt-oss-safeguard-20b supports a 131K-token context window and can output up to 66K tokens. It accepts text input.

Compare head-to-head