EmbeddingGemma 300M
sdn-embed-gemma-300mEmbeddingsLive in the catalogA 300M-parameter embedding that punches well above its size, with a 2K input window — four times what the BGE English models accept — so longer passages embed whole instead of being split first. A good fit when your chunks are paragraphs rather than sentences.
- 012K input — longer chunks without splitting
- 02Strong quality for its size
- 03768 dimensions, the common default width
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.
One endpoint. Served by our engine.
EmbeddingGemma 300M 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.
curl https://api.sideren.io/v1/embeddings \
-H "authorization: Bearer sdn_your_key" \
-H "content-type: application/json" \
-d '{
"model": "sdn-embed-gemma-300m",
"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.
Start free · no card · Starter from $5/mo