paraphrase-minilm-l6-v2 - API in Egypt, billed in EGP
LiveWe present a sentence similarity model based on the Sentence Transformers architecture, which maps sentences to a 384-dimensional dense vector space. The model uses a pre-trained BERT encoder and applies mean pooling on top of the contextualized word embeddings to obtain sentence embeddings. We evaluate the model on the Sentence Embeddings Benchmark.
Modality
Embedding
Context window
512 tokens
Region
US
Weights
Open weights
Published
Jul 14, 2026
Pricing
Input
0.33
EGP per 1M tokens
Output
Free
EGP per 1M tokens
Monthly cost example
16.25 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.
Use it via the API
paraphrase-minilm-l6-v2 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/embeddings — 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.embeddings.create(
model="paraphrase-minilm-l6-v2",
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: "paraphrase-minilm-l6-v2",
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": "paraphrase-minilm-l6-v2",
"input": "The food was delicious and the waiter...",
"encoding_format": "float"
}'Frequently asked questions
How much does paraphrase-minilm-l6-v2 cost?
0.33 EGP per 1M input tokens; Output tokens are free. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of paraphrase-minilm-l6-v2?
paraphrase-minilm-l6-v2 supports a context window of 512 tokens (512).
Where is paraphrase-minilm-l6-v2 hosted?
paraphrase-minilm-l6-v2 is served from US (US-hosted inference).
Is paraphrase-minilm-l6-v2 an open-weights model?
Yes — paraphrase-minilm-l6-v2 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 paraphrase-minilm-l6-v2 via the API?
paraphrase-minilm-l6-v2 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 "paraphrase-minilm-l6-v2" and your API key.