phi-4 - API in Egypt, billed in EGP
LivePhi-4 is a model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning.
Modality
Chat
Context window
16K tokens
Max output
15K tokens
Region
US
Weights
Open weights
Published
29 Sept 2026
Pricing
Input
4.01
EGP per 1M tokens
Output
8.02
EGP per 1M tokens
Monthly cost example
320.68 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.
Use it via the API
phi-4 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="phi-4",
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://dev-backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "phi-4",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://dev-backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "phi-4",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
How much does phi-4 cost?
4.01 EGP per 1M input tokens; 8.02 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of phi-4?
phi-4 supports a context window of 16,384 tokens (16K), with up to 14,745 output tokens per response.
Where is phi-4 hosted?
phi-4 is served from US (US-hosted inference).
Is phi-4 an open-weights model?
Yes — phi-4 is an open-weights model. You call it through the SovereignEG API like any other catalog model, with per-token EGP billing.
How do I use phi-4 via the API?
phi-4 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 "phi-4" and your API key.
Related models
View all models →WizardLM-2 8x22B
Microsoft · Chat · 66K context
35.50 EGP / 1M input tokens
AionLabs: Aion 3.5
aion-labs · Chat · 262K context
171.79 EGP / 1M input tokens
AionLabs: Aion 3.5 Mini
aion-labs · Chat · 262K context
40.09 EGP / 1M input tokens
AionLabs: Aion-2.0
aion-labs · Chat · 131K context
45.81 EGP / 1M input tokens