BGE Base En v1.5 Local

UK-hosted Introductory rate Embeddings

Our UK-hosted text-embedding model, served on our own GPU in our UK datacentre for search, retrieval-augmented generation (RAG), clustering and deduplication. Document text sent to embed never leaves our infrastructure. Priced on input tokens only.

What it's best for

Best for search, retrieval-augmented generation (RAG), clustering and deduplication. Embed your documents once, store the vectors, then retrieve the most relevant chunks at question time and hand them to a chat model for the answer. Priced on input tokens only.

Pricing

Prices updated daily; last generated 2026-07-12. This is an introductory rate while we confirm final pricing for our UK-hosted models.

Billing is metered per request in GBP on the same monthly invoice as your apps: no subscription, no minimum. We list every model once, at the cheapest route we can serve it on; if we have to fail over to a more expensive route, we absorb the difference and your price does not change.

Where your data is processed

BGE Base En v1.5 Local runs on GPUs we own, in our UK datacentre. Prompts and completions are processed entirely on Node infrastructure, under UK jurisdiction, and never leave it. There is no third-party AI provider in the data path and no US CLOUD Act exposure. If your workload is compliance-sensitive, this is the residency story to build on.

Call it in two minutes

The gateway is OpenAI-compatible: point your SDK or HTTP client at api.node.uk and use the model id bge-base-en-v1.5-local. Credentials come from your portal, with £25 of free credit on signup.

curl https://api.node.uk/api/v1/models/bge-base-en-v1.5-local/v1/embeddings \
  -H "Authorization: Bearer $NODE_GATEWAY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "bge-base-en-v1.5-local", "input": "The text to embed"}'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.node.uk/api/v1/models/bge-base-en-v1.5-local/v1",
    api_key=NODE_GATEWAY_TOKEN,
)

vectors = client.embeddings.create(
    model="bge-base-en-v1.5-local",
    input=["The text to embed"],
)

Related models

Browse the full model catalogue, read which model for which task, or see how the AI Gateway works.