Model card

BGE Base EN v1.5

sdn-bge-base-enEmbeddingsLive in the catalog

The balanced English embedding most retrieval stacks start with: 768 dimensions is wide enough to hold real semantic nuance and narrow enough to keep an index small and searches fast. If you are adding retrieval to a product and do not yet have a reason to choose otherwise, start here.

Max input1K tokens

Input · per Mtok$0.07

Dimensions768

AvailabilityLive

Where it earns its keep[01/03]

01768 dimensions — the common default width
02Balanced accuracy against index size
03Also reachable as sdn-embed

Capabilities

EmbeddingsYes

Turns text into a fixed-length vector for semantic search, RAG, clustering, and dedupe. Call it on /v1/embeddings with a string or array of inputs — no chat, tools, or reasoning.

Behind the endpoint[02/03]

One endpoint. Served by our engine.

BGE Base EN v1.5 is served through the Sideren engine — zero-downtime serving is the design target, not a status-page apology. You request it by name; everything else is our problem.

Call it by name

curl https://api.sideren.io/v1/embeddings \
  -H "authorization: Bearer sdn_your_key" \
  -H "content-type: application/json" \
  -d '{
    "model": "sdn-bge-base-en",
    "input": "text to embed"
  }'

OpenAI-style clients work too — POST the same model name to /v1/embeddings with a Bearer key. See the docs for both dialects.

Your agent doesn't change.
Everything underneath does.

$export ANTHROPIC_BASE_URL=https://api.sideren.io

Get a key Read the docs

Start free · no card · Starter from $5/mo

One endpoint. Served by our engine.

Your agent doesn't change.Everything underneath does.

Your agent doesn't change.
Everything underneath does.