Unified
One endpoint
Add an image_url part to your messages and the gateway routes to a multimodal model. No new SDK surface, no separate billing basis — it is chat with pictures.
Capability · Vision
Multimodal vision, on the chat endpoint.
Send images alongside text on the standard chat call. Routing biases to a vision-capable, region-resident model — no separate API to learn.
POST /v1/chat/completions (image_url parts)
What you get
Built for regulated workloads
Vision has no separate route — images ride /v1/chat/completions as image_url content parts, and routing biases toward a vision-capable model in your region. In Switzerland that is Infomaniak’s multimodal Gemma-4 31B; in the EU, Scaleway’s Gemma-4 and Qwen3.6. It is billed as ordinary chat tokens.
PHI
PHI vision in CH & EU
PHI vision runs on Infomaniak (CH) and Scaleway (EU) multimodal models under verified DPAs. US PHI vision is staged on Azure OpenAI (GPT-4o) and returns no_route until enabled.
Multimodal
Text + image reasoning
Ask questions about charts, scanned forms, wound photos or lab images in the same turn as text. The model answers in the normal chat response shape.
Residency
Resident by default
Images are processed in the region you pin and never stored. Where a region has no multimodal PHI host, the request is refused rather than re-routed.
Availability & pricing
Where it runs, what it costs
Every route is region-resident and the PHI gate is enforced per call. Prices include the flat +10% gateway margin and mirror the live /v1/pricing rate card.
| Region | Provider | Model | Tier | Price |
|---|---|---|---|---|
| CH | Infomaniak | gemma-4 31B (multimodal) | PHI | $0.24 / $0.48 |
| EU | Scaleway | gemma-4 26B / qwen3.6 35B | PHI | $0.30 / $0.59 |
| US | Azure OpenAI | gpt-4o (vision) | Staged | $2.75 / $11.00 |
| WORLD | Google / Anthropic | gemini / claude (vision) | General | see /pricing |
| Other | — | vision (PHI) | No route | CH/EU live |
Token-billed like chat (per 1M in / out), gateway margin included. US PHI vision is staged on Azure OpenAI; PHI vision is live in CH and EU.
Try it
A real call, end to end
Ask about an image in Switzerland — same chat call, with an image part.
curl
curl https://phi-cloud.com/api/v1/chat/completions \
-H "Authorization: Bearer $PHI_API_KEY" \
-H "X-Region: CH" -H "X-PHI: true" \
-d '{
"model": "gemma-4",
"messages": [{"role":"user","content":[
{"type":"text","text":"What does this form say?"},
{"type":"image_url","image_url":{"url":"data:image/png;base64,iVBOR..."}}
]}]
}'response
x-phi-routed: infomaniak-gemma-4-31b/CH/phi
x-phi-tier: phi
x-phi-usage: verifiedResidency & coverage
- CH PHI vision → Infomaniak Gemma-4 31B (multimodal, Swiss /2/ surface).
- EU PHI vision → Scaleway Gemma-4 / Qwen3.6.
- US PHI vision → staged on Azure OpenAI GPT-4o (no_route until enabled).
- General vision is available worldwide on Gemini / Claude; PHI vision is CH/EU today.
FAQ
Common questions
No. Vision is part of /v1/chat/completions — add an image_url content part and routing biases to a multimodal model. This keeps one endpoint, one billing basis, one set of audit headers.
Not in production yet. US PHI vision is staged on Azure OpenAI GPT-4o and returns no_route until the deployment is enabled. CH and EU PHI vision are live.
Ready when you are
Put vision in production — without giving up your data.
Spin up a key in minutes. The residency and PHI posture above arrives unchanged.
Free to test · Prepaid credits, no subscription · No data retained