bge-m3 - API for Egypt, billed in EGP
Live
BGE-M3 is a versatile text embedding model that supports multi-functionality, multi-linguality, and multi-granularity, allowing it to perform dense retrieval, multi-vector retrieval, and sparse retrieval in over 100 languages and with input sizes up to 8192 tokens. The model can be used in a retrieval pipeline with hybrid retrieval and re-ranking to achieve higher accuracy and stronger generalization capabilities. BGE-M3 has shown state-of-the-art performance on several benchmarks, including MKQA, MLDR, and NarritiveQA, and can be used as a drop-in replacement for other embedding models like DPR and BGE-v1.5.
Modality
Embedding
Context window
8K tokens
Region
US
Weights
Open weights
Published
14 Jul 2026
Pricing
Input
0.61
EGP per 1M tokens
Output
—
EGP per 1M tokens
Monthly cost example
30.29 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model’s catalog rates.
Use it via the API
bge-m3 works with any OpenAI-compatible SDK — point the base URL at https://backend.sovereigneg.com/v1 and use your SovereignEG API key.
Run inference
POST /v1/embeddings — OpenAI-compatible: SovereignEG's own seg-sdk, or a drop-in for any OpenAI SDK.
from seg import SEG # pip install seg-sdk
client = SEG(api_key="YOUR_API_KEY")
response = client.embeddings.create(
model="bge-m3",
input="The food was delicious and the waiter...",
encoding_format="float",
)
vector = response.data[0].embedding
print(f"dim={len(vector)}, first 8 dims: {vector[:8]}")from openai import OpenAI
client = OpenAI(
base_url="https://backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.embeddings.create(
model="bge-m3",
input="The food was delicious and the waiter...",
encoding_format="float",
)
vector = response.data[0].embedding
print(f"dim={len(vector)}, first 8 dims: {vector[:8]}")import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.embeddings.create({
model: "bge-m3",
input: "The food was delicious and the waiter...",
encoding_format: "float",
})
const vector = response.data[0].embedding
console.log(`dim=${vector.length}, first 8 dims:`, vector.slice(0, 8))curl https://backend.sovereigneg.com/v1/embeddings \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "bge-m3",
"input": "The food was delicious and the waiter...",
"encoding_format": "float"
}'Frequently asked questions
How much does bge-m3 cost?
0.61 EGP per 1M input tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of bge-m3?
bge-m3 supports a context window of 8,192 tokens (8K).
Where is bge-m3 hosted?
bge-m3 is served from US (US-hosted inference).
Is bge-m3 an open-weights model?
Yes — bge-m3 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 bge-m3 via the API?
bge-m3 is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://backend.sovereigneg.com/v1 and call /v1/embeddings with model "bge-m3" and your API key.