All models

BGEBAAIOpen weights

BGE-M3.

BGE-M3 is a multilingual embedding model with long context, versatile for RAG pipelines.

Get started → Providers and prices

base_url="https://api.noirdoc.de/v1" model="BAAI/bge-m3"

  • Data centres in Germany
  • § 203 confidentiality
  • Zero retention
  • List prices

Details.

Where the model runs, which rules apply and what it can do.

  1. Data centres in Germany IONOS · weber.cloud Contracting party: IONOS Cloud GmbH · based in Montabaur, GermanyContracting party: weber.digital GmbH · based in Balingen, Germany
§ 203 German Criminal Code (StGB)
Confidentiality agreed with IONOS and weber.cloud
Weights
Open weights
See how this looks in your account →
Map: BGE-M3 runs in data centres in Germany (IONOS, weber.cloud).

Providers.

We offer BGE-M3 through these providers.

Provider § 203 model=
List price · € Input Cache Read Cache Write Output
IONOS DE German data centres
§ 203 agreed
BAAI/bge-m3
0.02 € per 1M tokens
weber.cloud DE Own data centres in Germany
§ 203 agreed
baai/bge-m3
0.02 € per 1M tokens

More models.

The Beijing Academy of Artificial Intelligence develops the BGE embeddings for English and multilingual retrieval pipelines.

All BGE models →
Model
List price · € Input Cache Read Cache Write Output
BGE Large EN v1.5 Embeddings Strong English embeddings for high-quality retrieval pipelines. IONOS Logo IONOS · DE
0.015 € per 1M tokens

Get started.

Test selected models right away with €5 starter credit — every model from the first top-up. If you have questions first, talk to our sales team.

Sign in →
python · openai sdk api.noirdoc.de/v1 
import os
from openai import OpenAI

client = OpenAI(
    # one line, that's all
    base_url="https://api.noirdoc.de/v1",
    api_key=os.environ["NOIRDOC_API_KEY"],
)

response = client.embeddings.create(
    model="BAAI/bge-m3",  # provider & model
    input="Hello",
)