DeepSeek: DeepSeek V3.1 - API in Egypt, billed in EGP
Livedeepseek-chat-v3.1DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context
Modality
Chat
Context window
161K tokens
Max output
145K tokens
Region
US
Published
20 Aug 2026
Pricing
Input
30.39
EGP per 1M tokens
Output
91.17
EGP per 1M tokens
Monthly cost example
2,886.95 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.
Use it via the API
DeepSeek: DeepSeek V3.1 works with any OpenAI-compatible SDK — point the base URL at https://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://backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="deepseek-chat-v3.1",
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://backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "deepseek-chat-v3.1",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-chat-v3.1",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
How much does DeepSeek: DeepSeek V3.1 cost?
30.39 EGP per 1M input tokens; 91.17 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of DeepSeek: DeepSeek V3.1?
DeepSeek: DeepSeek V3.1 supports a context window of 161,000 tokens (161K), with up to 144,900 output tokens per response.
Where is DeepSeek: DeepSeek V3.1 hosted?
DeepSeek: DeepSeek V3.1 is served from US (US-hosted inference).
How do I use DeepSeek: DeepSeek V3.1 via the API?
DeepSeek: DeepSeek V3.1 is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://backend.sovereigneg.com/v1 and call /v1/chat/completions with model "deepseek-chat-v3.1" and your API key.
Related models
View all models →DeepSeek: DeepSeek V3 0324
DeepSeek · Chat · 164K context
13.81 EGP / 1M input tokens
DeepSeek: DeepSeek V4 Flash 0731
DeepSeek · Chat · 1M context
4.42 EGP / 1M input tokens
DeepSeek: DeepSeek V4 Pro 0813
DeepSeek · Chat · 1M context
71.83 EGP / 1M input tokens
DeepSeek: R1
DeepSeek · Chat · 64K context
38.68 EGP / 1M input tokens