Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. OpenAI

GPT OSS Safeguard 20B

gpt-oss-safeguard is a first open weight reasoning model specifically trained for safety classification tasks to help classify text content based on customizable policies. As a fine-tuned version of gpt-oss, gpt-oss-safeguard is designed to follow explicit written policies that you provide. This enables bring-your-own-policy Trust & Safety AI, where your own taxonomy, definitions, and thresholds guide classification decisions. Well crafted policies unlock gpt-oss-safeguard's reasoning capabilities, enabling it to handle nuanced content, explain borderline decisions, and adapt to contextual factors.

  • Reasoning

Added Feb 23, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.075
Output
$0.30
Compare provider prices

Specifications

Context window
131.1K
Max output
65.5K
Parameters
20B / 3.6B
Total / active

Benchmarks

No public benchmark scores for this model yet.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.075$0.30N/AN/AN/A
Auto
Auto (Anonymized)
$0.075$0.30N/AN/AN/A
Kitani
Kitani
MXFP4
GLB
$0.0709$0.294$0.0354N/AN/A
Groq
Groq
US
$0.0787$0.315$0.0394N/AN/A
Privacy:ZDR, prompts not retainedNo training on prompts
Batch API
ProviderInputOutputCached input
Auto
Autoopenai/gpt-oss-safeguard-20b
$0.075/M$0.30/MN/A

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare GPT OSS Safeguard 20B with similar models from the same provider or model family.

GPT OSS 20B

openai/gpt-oss-20b

An open-weight 21B parameter model released under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI's Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

GPT OSS 120B

openai/gpt-oss-120b

An open-weight, 117B-parameter Mixture-of-Experts (MoE) language model designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

GPT 6.1 Terra Pro

openai/gpt-6.1-terra-pro

GPT-6.1 Terra Pro uses the same underlying model as GPT-6.1 Terra with Pro reasoning mode enabled for higher-quality responses on complex tasks.

GPT 6.1 Terra

openai/gpt-6.1-terra

GPT-6.1 Terra is a fast, efficient model for everyday work, with strong visual reasoning, clearer writing, and capable coding at half GPT-6.1 Sol’s standard token prices. It supports text and image input, tool calling, structured outputs, and optional reasoning from none through max.

GPT 6.1 Sol

openai/gpt-6.1-sol

GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It supports text and image input, tool calling, structured outputs, and reasoning from low through max.

GPT 6.1 Sol Pro

openai/gpt-6.1-sol-pro

GPT-6.1 Sol Pro uses the same underlying model as GPT-6.1 Sol with Pro reasoning mode enabled for higher-quality responses on complex tasks.