gpt-oss-20b
Livegpt-oss-20b is an open-weight 21B parameter model released by OpenAI 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. 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.
Modality
Chat
Context window
131K tokens
Max output
16K tokens
Region
US
Published
Jul 21, 2026
Pricing
Input
1.69
EGP per 1M tokens
Output
7.87
EGP per 1M tokens
Use it via the API
gpt-oss-20b works with any OpenAI-compatible SDK — point the base URL at https://preprod-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://preprod-backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="gpt-oss-20b",
messages=[
{"role": "user", "content": "What are some fun things to do in Cairo?"}
],
)
print(response.choices[0].message.content)import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://preprod-backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "gpt-oss-20b",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://preprod-backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-oss-20b",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
How much does gpt-oss-20b cost?
1.69 EGP per 1M input tokens; 7.87 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of gpt-oss-20b?
gpt-oss-20b supports a context window of 131,072 tokens (131K), with up to 16,384 output tokens per response.
Where is gpt-oss-20b hosted?
gpt-oss-20b is served from US (US-hosted inference).
How do I use gpt-oss-20b via the API?
gpt-oss-20b is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://preprod-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "gpt-oss-20b" and your API key.