OpenAI: gpt-oss-safeguard-20b - API in Egypt, billed in EGP

Live
OpenAIgpt-oss-safeguard-20b

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

Modality

Chat

Context window

131K tokens

Max output

66K tokens

Region

US

Published

29 Sept 2026

Pricing

Input

4.30

EGP per 1M tokens

Output

17.19

EGP per 1M tokens

Monthly cost example

472.74 EGP

Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.

Use it via the API

OpenAI: gpt-oss-safeguard-20b works with any OpenAI-compatible SDK — point the base URL at https://dev-backend.sovereigneg.com/v1 and use your SovereignEG API key.

Run inference

OpenAI-compatible — POST /v1/chat/completions — drop-in for any OpenAI SDK.

from openai import OpenAI

client = OpenAI(
    base_url="https://dev-backend.sovereigneg.com/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="gpt-oss-safeguard-20b",
    messages=[
        {"role": "user", "content": "What are some fun things to do in Cairo?"}
    ],
)

print(response.choices[0].message.content)

Frequently asked questions

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

4.30 EGP per 1M input tokens; 17.19 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.

What is the context window of OpenAI: gpt-oss-safeguard-20b?

OpenAI: gpt-oss-safeguard-20b supports a context window of 131,072 tokens (131K), with up to 65,536 output tokens per response.

Where is OpenAI: gpt-oss-safeguard-20b hosted?

OpenAI: gpt-oss-safeguard-20b is served from US (US-hosted inference).

How do I use OpenAI: gpt-oss-safeguard-20b via the API?

OpenAI: gpt-oss-safeguard-20b is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://dev-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "gpt-oss-safeguard-20b" and your API key.