01 · Portable
Capability · Embeddings
Embeddings in one shared vector space.
A single 4096-dimension embedding model wherever embeddings run (CH and EU today) — for general and PHI traffic alike — so your vectors stay comparable across jurisdictions.
POST /v1/embeddings
What you get
Built for regulated workloads
Embeddings resolve to the canonical qwen3-embedding-8b (4096-d) in production in CH (Infomaniak) and EU (Scaleway), for both general and PHI traffic. Because the model is the same in both regions, a vector embedded in Zurich is directly comparable to one embedded in Paris, so you can build one index that spans jurisdictions. US and other regions return no_route until the staged Fireworks (US) and Azure/Bedrock (ROW) rows — all in the same 4096-d space — are enabled.
02 · Same-space failover
Dimension-safe routing
03 · PHI
PHI embeddings, resident
04 · Options
Pin a different space
Availability & pricing
Where it runs, what it costs
Every route is pinned to a region, PHI stays on resident hosts, and the PHI gate is enforced per call. Prices mirror the live /v1/pricing rate card.
| Region | Provider | Model | Tier | Price |
|---|---|---|---|---|
| CH | Infomaniak | qwen3-embedding-8b · 4096-d | PHI | $0.14 / 1M |
| EU | Scaleway | qwen3-embedding-8b · 4096-d | PHI | $0.19 / 1M |
| US | Fireworks | qwen3-embedding-8b · 4096-d | Staged | $0.17 / 1M |
| CH | Infomaniak | bge-multilingual-gemma2 · 3584-d | PHI | $0.13 / 1M |
| CH | Infomaniak | all-MiniLM-L12-v2 · 384-d | PHI | Free |
Per 1M input tokens. The canonical qwen3-embedding-8b is the default wherever embeddings run (CH and EU); other regions return no_route. bge / minilm are pin-only CH options in their own dimension.
Try it
A real call, end to end
Embed a batch in the EU. The response is a standard OpenAI embedding object; the headers confirm the route and space.
Residency & vectors
- CH embeddings stay on Infomaniak via the Swiss /2/ AI surface.
- EU embeddings run on Scaleway, in the same 4096-d space as CH.
- US and other regions return no_route until the staged Fireworks (US) and Azure/Bedrock (ROW) rows are enabled.
- Build one cross-jurisdiction index; the shared space keeps similarity scores meaningful.
curl https://cloudsitus.com/api/v1/embeddings \
-H "Authorization: Bearer $PHI_API_KEY" \
-H "X-Region: EU" \
-H "X-PHI: true" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-embedding-8b",
"input": ["patient presents with...", "follow-up in two weeks"]
}'x-phi-routed: scaleway-qwen3-embedding-8b/EU/phi
x-phi-tier: phi
x-phi-usage: verified
# data[].embedding -> 4096 floatsWhy one embedding model instead of the best per region?
Can I mix embedding models in the same index?
Are PHI embeddings available in the US?
Ready when you are
Put embeddings & search in production — without giving up your data.
Spin up a key in minutes. The residency and PHI posture above arrives unchanged.
Prepaid credits from $10 · No subscription · No data retained