AI InferenceBuilt for Egypt
An OpenAI-compatible inference API for Egypt and MENA. Billed in EGP. Sovereign path for regulated workloads.
One API. Every model.
Chat, embedding and multimodal models from the live catalog — EGP rates, context windows, and modalities, all behind one OpenAI-compatible endpoint.
Arcee AI: Trinity Large Thinking
arcee-ai
Input / 1M
14.3EGP
Output / 1M
45.8EGP
Context
262k ctx
all-minilm-l12-v2
SBERT
Input / 1M
0.33EGP
Output / 1M
Free
Context
512 ctx
Arize AI Qwen 2 1.5B Instruct
arize-ai
Input / 1M
5.72EGP
Output / 1M
5.72EGP
Context
33k ctx
all-minilm-l6-v2
SBERT
Input / 1M
0.33EGP
Output / 1M
Free
Context
512 ctx
Claude Opus 4.5
Anthropic
Input / 1M
278EGP
Output / 1M
1.4kEGP
Context
200k ctx
all-mpnet-base-v2
SBERT
Input / 1M
0.33EGP
Output / 1M
Free
Context
512 ctx
Local currency. No FX. No surprises.
Pay-as-you-go from prepaid credit. Per-million-token rates from the live catalog — exact pricing in the dashboard.
meta-llama-3.1-8b-instruct-turbo
Meta · chat
Input / 1M
1.14EGP
Output / 1M
1.72EGP
Est. monthly*
83EGP
deepseek-v3
DeepSeek · chat
Input / 1M
18.3EGP
Output / 1M
50.9EGP
Est. monthly*
1,679EGP
embeddinggemma-300m
Google · embed
Input / 1M
0.13EGP
Output / 1M
Free
Est. monthly*
6.5EGP
* Illustrative monthly total for 50M input + 15M output tokens on chat models (embeddings bill input only). Amounts in EGP.
Browse the full catalogThree lines of code.
Any model.
Invoiced in EGP.
Get your API key
Sign up, create an organization, and create an API key from the dashboard.
Pick a model
Browse the catalog with EGP pricing and context windows side-by-side.
Ship in EGP
Drop-in OpenAI SDK call. Use prepaid credits from your account balance.
from openai import OpenAI
client = OpenAI(
base_url="https://backend.sovereigneg.com/v1",
api_key="sk-...",
)
response = client.chat.completions.create(
model="gpt-oss-20b", # any model id from the catalog
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Enterprise AI controls, built in.
Everything a procurement team asks about — orgs, roles, spend caps, audit logs, and a written security review — is in the product today, not on a roadmap slide.
Organizations & projects
Two-tier hierarchy mirroring OpenAI: orgs own billing, projects own keys and usage. Each project has its own model allow-list.
Members & roles
Invite-by-email with preset roles (Owner / Admin / Developer / Viewer). Role-based access is enforced on every API and dashboard request.
API keys with guardrails
Per-key scopes, IP allow-lists, monthly EGP spend caps, RPM limits, automatic expiry, one-shot reveal, instant revoke.
Admin audit trail
Every key create, key revoke, member change, and model update lands in an append-only audit log.
EGP-native billing
Pay-as-you-go from a prepaid EGP credit balance. Manual or coupon top-up, transaction history per org, invoice workflow coming later.
Per-project spend caps
Hard monthly spend ceiling per project, enforced automatically with a clear error when the cap is hit.
From cloud API to sovereign AI hosting in Egypt — one product.
Same API surface, same EGP billing path. Customers don’t re-integrate when their workload moves sovereign.
Standard routing — live today
Available nowOne OpenAI-compatible endpoint. Requests are routed to vetted upstream providers and billed in EGP. Best for product teams shipping today.
Unified API
One endpoint for chat and embeddings. The OpenAI SDK works with zero rewrites.
Live model catalog
Browse every available model with per-1M-token EGP pricing in the dashboard.
EGP credit balance
Prepaid credits with manual top-up requests reviewed by our team.
Sovereign deployment — Egypt-hosted
Design partnersDedicated GPU capacity hosted inside Egypt for regulated workloads. Currently in private design-partner phase.
Egypt-hosted capacity
Dedicated deployments inside Egypt for approved design partners, not the default public route.
Private deployment
Isolated capacity per customer; sized and procured per design-partner contract.
Designed for PDPL
Designed to support Egypt Personal Data Protection Law and sector-specific data-residency rules.
Two ways to start.
Developers self-serve. Regulated enterprises talk to us first.
AI access today. Enterprise governance now. Sovereign hosting next.