BGE-M3

baai/bge-m3

available embedding hosted in India zero_retention

BAAI's BGE embedding models are a widely used open-weight choice for multilingual retrieval.

Context window 8,192 tokens

Input ₹1.20 per million tokens

Output ₹0.00 per million tokens

Licence varies verify before production use

Call this model

from openai import OpenAI client = OpenAI( base_url="https://www.thaliai.in/api/v1", api_key="thali-sk-...", ) completion = client.chat.completions.create( model="baai/bge-m3", messages=[{"role": "user", "content": "Hello"}], )

Works with any OpenAI SDK. Streaming, fallback lists and provider preferences are documented in the routing guide.

This model serves from infrastructure in India. Prompts and completions are processed in-country and never stored.