01 · Per model
Every model has its own price
Each model is priced per million tokens — not a repackaged flat fee. A model in Switzerland or the EU is often 5–10× cheaper than a US frontier model, and the table below shows exactly which is which.
Pricing
Pay per call, priced per model.
Buy credits up front — 300 credits = $1, $10 (3,000 credits) to start — and draw them down as you call. One prepaid credit balance for every model you run, one listed price per model, and PHI routing carries no surcharge. No subscription, no seats — you spend only the credits you buy.
- 3,000 credits for $10 to start
- Pay-as-you-go credit drawdown
- No subscription, no seats
CloudSitus · CH
$ POST /v1/chat/completions X-PHI: true X-Region: CH < HTTP/2 200 < x-phi-tier: phi < x-phi-routed: infomaniak-nemotron-nano-30b/CH/phi < x-phi-attempts: 1
How pricing works
Simple pricing, and nothing hidden behind it.
Buy credits up front (300 credits = $1), then each call draws its listed per-model price down from your credit balance. Here is every part of it, with nothing you have to read the fine print to find.
02 · One price
The same price at every volume
No tiers, no enterprise upcharge, no platform fee. The price in the table below is what every call costs, whatever your volume.
03 · PHI included
No surcharge to route PHI
Pinning a request to a PHI-eligible provider costs nothing extra. The PHI tier is priced exactly like any other route — privacy is not a premium.
04 · Prepaid credits
Buy credits, draw them down
Top up a credit balance through Stripe at 300 credits = $1 — $10 (3,000 credits) minimum, in preset packs ($10 / $20 / $50 / $100) or a custom amount. Each call draws down credits at its listed price, rescaled to 300 credits/$. Pay in your local currency at rounded parity (a $20 pack shows as €20 / £20 / CHF 20); receipts settle in your chosen currency and credits are granted at the USD-parity value.
05 · No subscription
No seats. No monthly commitment.
There are no per-user licenses and no recurring plan. You only ever spend the credits you buy — turn on auto-recharge to top up your credit balance automatically when it runs low, or top up by hand.
06 · Free diagnostic
Check your setup for free
GET /v1/ping validates your key and dry-runs routing without touching an upstream or spending a credit — so you can confirm auth, region residency and billing status before your first real call.
A worked example
1M in + 1M out on the PHI tier
Send one million input tokens and receive one million output tokens through Mistral 24B (Infomaniak, CH). At $0.50 in and $1.50 out per million, the whole run lands at the price below — PHI routing at no extra cost.
infomaniak-mistral-24b
- 1M input tokens
- $0.50
- 1M output tokens
- $1.50
- Total
- $2.00
Model prices
Every model, every rate, on one page.
Listed per 1M tokens. Each row shows the region it is served in (and “processed globally” where the vendor publishes no residency for it), whether it's PHI-eligible, and a quality tier (Low / Medium / High). Regional models are often 5–10× cheaper than US frontier models.
Catalogue as of 2026-11-06. Prices can change between site updates — GET /v1/pricing always serves the current rate, and that is what a call is billed at.
Scroll the table sideways for prices →
| Model | Region | PHI | Tier | In / 1M | Out / 1M |
|---|---|---|---|---|---|
Mistral 3 (Infomaniak, CH) infomaniak-mistral-3 | CH | eligible | Low | $0.33 | $1.00 |
Qwen3 (Infomaniak, CH) infomaniak-qwen3 | CH | eligible | Medium | $0.50 | $1.50 |
Laya System-One · multilingual (Laya, CH) laya-multilingual | CH | general | Medium | $0.06 | — |
Mistral 24B (Infomaniak, CH) infomaniak-mistral-24b | CH | eligible | Low | $0.50 | $1.50 |
Laya System-One · English (Laya, CH) laya-english | CH | general | Medium | $0.06 | — |
Laya System-One · typed decisions (Laya, CH) laya-typed-decisions | CH | general | Medium | $0.06 | — |
All-MiniLM-L12-v2 (Infomaniak, CH) infomaniak-minilm-l12-v2 | CH | eligible | Low | Free | — |
Kimi K2.6 · chat + code + vision (Infomaniak, CH) infomaniak-kimi-k2-6 | CH | eligible | High | $1.23 | $6.14 |
Qwen3.5 397B A17B (Infomaniak, CH) infomaniak-qwen3-5-397b | CH | eligible | High | $1.64 | $7.36 |
Qwen3-Embedding-8B · 4096-d (Infomaniak, CH) infomaniak-qwen3-embedding-8b | CH | eligible | High | $0.14 | — |
Nemotron 3 Nano 30B A3B (Infomaniak, CH) infomaniak-nemotron-nano-30b | CH | eligible | Low | $0.10 | $0.41 |
Gemma-4 31B IT · vision (Infomaniak, CH) infomaniak-gemma-4-31b | CH | eligible | Medium | $0.41 | $0.82 |
BGE-Multilingual-Gemma2 · 3584-d (Infomaniak, CH) infomaniak-bge-gemma2 | CH | eligible | High | $0.13 | — |
GPT-5 mini gpt-5-mini | EU processed globally | general | Low | $0.42 | $3.33 |
GPT-5.6 Terra gpt-5-6-terra | EU processed globally | general | High | $3.33 | $20.00 |
GPT-5.6 Luna gpt-5-6-luna | EU processed globally | general | Low | $0.33 | $2.00 |
GPT-6 Astra gpt-6-astra | EU processed globally | general | High | $16.67 | $83.33 |
Claude Haiku 4.5 claude-haiku-4-5 | EU processed globally | general | Low | $1.67 | $8.33 |
Claude Sonnet 5 claude-sonnet-5 | EU processed globally | general | High | $3.33 | $16.67 |
Claude Fable 5 claude-fable-5 | EU processed globally | general | High | $16.67 | $83.33 |
Mistral Small mistral-small | EU | general | Low | $0.25 | $1.00 |
Gemini 3.8 Flash gemini-3-8-flash | EU processed globally | general | Low | $1.25 | $6.25 |
Claude Fable 5.1 claude-fable-5-1 | EU processed globally | general | High | $16.67 | $83.33 |
Gemini 3.1 Flash Lite gemini-3-1-flash-lite | EU processed globally | general | Low | $0.42 | $2.50 |
gpt-5-nano gpt-5-nano | EU processed globally | general | Low | $0.08 | $0.67 |
gpt-5.4 gpt-5-4 | EU processed globally | general | High | $4.17 | $25.00 |
gpt-5.4-mini gpt-5-4-mini | EU processed globally | general | Low | $1.25 | $7.50 |
gpt-5.4-nano gpt-5-4-nano | EU processed globally | general | Low | $0.33 | $2.08 |
Gemini 3.5 Flash Lite gemini-3-5-flash-lite | EU processed globally | general | Low | $0.50 | $4.17 |
gpt-5.5 gpt-5-5 | EU processed globally | general | High | $8.33 | $50.00 |
gpt-6-luna gpt-6-luna | EU processed globally | general | Low | $0.17 | $0.83 |
gpt-6-sol gpt-6-sol | EU processed globally | general | High | $3.33 | $16.67 |
gpt-6.1-sol gpt-6-1-sol | EU processed globally | general | High | $3.33 | $16.67 |
Gemma-4 26B IT · vision (Scaleway, EU) scaleway-gemma-4-26b | EU | eligible | Medium | $0.48 | $0.96 |
Mistral Medium 3.5 mistral-medium-3-5 | EU | general | High | $2.50 | $12.50 |
Qwen3-Embedding-8B · 4096-d (Scaleway, EU) scaleway-qwen3-embedding-8b | EU | eligible | High | $0.19 | — |
Gemini 3.7 Flash gemini-3-7-flash | EU processed globally | general | Low | $1.25 | $6.25 |
Claude Opus 5 claude-opus-5 | EU processed globally | general | High | $8.33 | $41.67 |
Claude Sonnet 5.5 claude-sonnet-5-5 | EU processed globally | general | Medium | $3.33 | $16.67 |
mistral-large-latest mistral-large-latest | EU | general | Low | $0.83 | $2.50 |
Claude Opus 5.5 claude-opus-5-5 | EU processed globally | general | High | $6.67 | $33.33 |
Gemini 3.1 Pro (Preview) gemini-3-1-pro-preview | EU processed globally | general | High | $3.33 | $20.00 |
Qwen3.5 397B A17B · math/reasoning (Scaleway, EU) scaleway-qwen3-5-397b | EU | eligible | High | $1.15 | $6.90 |
Qwen3.6 35B A3B · code + vision (Scaleway, EU) scaleway-qwen3-6-35b | EU | eligible | Medium | $0.48 | $2.87 |
GPT-5 mini gpt-5-mini | US processed globally | general | Low | $0.42 | $3.33 |
GPT-5.6 Terra gpt-5-6-terra | US processed globally | general | High | $3.33 | $20.00 |
GPT-5.6 Luna gpt-5-6-luna | US processed globally | general | Low | $0.33 | $2.00 |
GPT-6 Astra gpt-6-astra | US processed globally | general | High | $16.67 | $83.33 |
Claude Haiku 4.5 claude-haiku-4-5 | US processed globally | general | Low | $1.67 | $8.33 |
Claude Sonnet 5 claude-sonnet-5 | US processed globally | general | High | $3.33 | $16.67 |
Claude Fable 5 claude-fable-5 | US processed globally | general | High | $16.67 | $83.33 |
Gemini 3.8 Flash gemini-3-8-flash | US processed globally | general | Low | $1.25 | $6.25 |
Claude Fable 5.1 claude-fable-5-1 | US processed globally | general | High | $16.67 | $83.33 |
Muse Spark 1.3 muse-spark-1-3 | US processed globally | general | High | $2.08 | $7.08 |
DeepSeek V4.1 Flash · chat + code (Together, US) together-deepseek-v4-1-flash | US | general | Medium | $0.50 | $2.00 |
GLM-5.3 · chat + code (Together, US) together-glm-5-3 | US | general | High | $2.33 | $7.33 |
DeepSeek V4 Flash · chat + code (Together, US) together-deepseek-v4-flash | US | general | Medium | $0.23 | $0.47 |
GLM-5.3-Flash · cheap chat + code + vision (Z.ai native) zai-glm-5-3-flash | US processed globally | general | Medium | $0.25 | $0.83 |
DeepSeek V4 Pro · chat + code (Together, US) together-deepseek-v4-pro | US | general | High | $2.20 | $6.60 |
GLM-5.2 · chat + code (Together, US) together-glm-5-2 | US | general | High | $2.33 | $7.33 |
GLM-5.2 · chat + code (Z.ai native) zai-glm-5-2 | US processed globally | general | High | $2.33 | $7.33 |
Kimi K3 · chat + code + vision (Moonshot native) kimi-k3 | US processed globally | general | High | $5.00 | $25.00 |
GLM-5.3 · chat + code (Z.ai native) zai-glm-5-3 | US processed globally | general | High | $2.33 | $7.33 |
MiniMax M3 · agentic chat + code (Together, US) together-minimax-m3 | US | general | Medium | $0.50 | $2.00 |
Mercury 2 · diffusion LLM (Inception Labs, US) inception-mercury-2 | US | general | Medium | $0.42 | $1.25 |
Mercury 2.5 · diffusion LLM (Inception Labs, US) inception-mercury-2-5 | US | general | Medium | $0.07 | $0.25 |
Gemini 3.1 Flash Lite gemini-3-1-flash-lite | US processed globally | general | Low | $0.42 | $2.50 |
gpt-5-nano gpt-5-nano | US processed globally | general | Low | $0.08 | $0.67 |
gpt-5.4 gpt-5-4 | US processed globally | general | High | $4.17 | $25.00 |
gpt-5.4-mini gpt-5-4-mini | US processed globally | general | Low | $1.25 | $7.50 |
gpt-5.4-nano gpt-5-4-nano | US processed globally | general | Low | $0.33 | $2.08 |
Gemini 3.5 Flash Lite gemini-3-5-flash-lite | US processed globally | general | Low | $0.50 | $4.17 |
gpt-5.5 gpt-5-5 | US processed globally | general | High | $8.33 | $50.00 |
gpt-6-luna gpt-6-luna | US processed globally | general | Low | $0.17 | $0.83 |
gpt-6-sol gpt-6-sol | US processed globally | general | High | $3.33 | $16.67 |
gpt-6.1-sol gpt-6-1-sol | US processed globally | general | High | $3.33 | $16.67 |
kimi-k2.6 (Moonshot native) kimi-k2-6 | US processed globally | general | Low | $1.58 | $6.67 |
Gemini 3.7 Flash gemini-3-7-flash | US processed globally | general | Low | $1.25 | $6.25 |
Muse Spark 1.2 muse-spark-1-2 | US processed globally | general | High | $2.08 | $7.08 |
Claude Opus 5 claude-opus-5 | US processed globally | general | High | $8.33 | $41.67 |
Kimi K3 (Together, US) together-kimi-k3 | US | general | High | $5.00 | $25.00 |
Claude Sonnet 5.5 claude-sonnet-5-5 | US processed globally | general | Medium | $3.33 | $16.67 |
Claude Opus 5.5 claude-opus-5-5 | US processed globally | general | High | $6.67 | $33.33 |
Gemini 3.1 Pro (Preview) gemini-3-1-pro-preview | US processed globally | general | High | $3.33 | $20.00 |
kimi-k2.7-code (Moonshot native) kimi-k2-7-code | US processed globally | general | Low | $1.58 | $6.67 |
GLM-5.3-Flash · cheap chat + code + vision (Together, US) together-glm-5-3-flash | US | general | Medium | $0.25 | $0.83 |
Prices are USD per 1M model tokens (the prompt/completion tokens a model counts) — not to be confused with credits, the prepaid balance your wallet holds at 300 credits = $1. Credits are what you buy; tokens are what the model counts. These are the CH / EU / US token models; audio, OCR and image/video price per minute / page / image / second. The Swiss laya-* decision rows price per encoder input token and have no output price — nothing is generated — but the state is re-encoded once per question, so an N-question decision costs roughly N× that state's tokens. The same rows — with quality_tier and phi_eligible per model — are served, always current, at GET /v1/pricing, and the full catalog (all regions + capabilities) at GET /v1/models.
FAQ
Questions a compliance team asks.
The short, honest answers — the kind that survive a security review.
Do I need a BAA to use CloudSitus?
It depends on your jurisdiction. US PHI for OCR, speech-to-text and text-to-speech runs on Azure under the Microsoft HIPAA BAA; US chat, vision and embeddings PHI are not available. Swiss and EU PHI run under nFADP/GDPR data-processing agreements (Infomaniak/Azure in CH, Scaleway/Azure in the EU) — that is nFADP/GDPR, not HIPAA. The PHI guarantee is the router pinning PHI to an eligible resident provider in your region. Ask us about the right paperwork for your jurisdiction.
Which providers can process PHI?
PHI is region-resident: in Switzerland it routes to Infomaniak or Azure (CH); in the EU to Scaleway or Azure (EU); in the US to Azure (US) for OCR, speech-to-text and text-to-speech only — US chat, vision and embeddings PHI are refused. OpenAI, Anthropic, Google, Mistral and Together AI serve general (non-PHI) traffic only.
Where does my data go?
You pin the region with X-Region (CH, EU, US, …). PHI is filtered to providers eligible in that region; if none are eligible, the request is refused (403 phi_blocked, or 422 no_route where nothing in the region serves that modality) rather than silently crossing a border.
Do you train on my data?
CloudSitus never trains on your data — it is a stateless proxy and stores no prompts or responses. PHI only reaches providers whose DPA or BAA we have reviewed. General traffic is governed by each vendor’s own API terms; where a vendor offers a per-request training opt-out (Deepgram), we send it on every call.
What happens if CloudSitus is breached?
No database holds tenant data (a separate database holds the public model catalogue only), and there is no payload logging — requests authenticate with HMAC-signed self-contained tokens. There is no stored prompt/response content to exfiltrate; usage reaches Stripe as amounts aggregated per model and region.
Will it work with my existing AI code?
Yes — point your existing client at https://cloudsitus.com/api/v1 and it works with no rewrite. Live endpoints cover chat (with image/vision input), embeddings, speech-to-text, text-to-speech, OCR, and /v1/models.
What does it cost?
CloudSitus is prepaid in credits: you buy a credit balance up front (300 credits = $1) and draw it down as you call, at each model's listed per-token price, rescaled to 300 credits/$. You can validate your key and dry-run routing for free with GET /v1/ping before adding credits. No PHI surcharge, no per-seat fees, no subscription. You can pay in your local currency at rounded parity (a $20 pack shows as €20 / £20 / CHF 20); receipts settle in your chosen currency and credits are granted at the USD-parity value.
Are credits the same as the model tokens I see in prices?
No — that's exactly why they have different names. Credits are your prepaid balance, fixed at 300 credits = $1; tokens are what the model counts (the prompt/completion tokens). Model prices on the pricing page are quoted in USD per million model tokens; when you make a call we compute the dollar cost from those model-token counts at the model's listed price and deduct the equivalent credits at 300/$. So 1 credit does not equal 1 model token.
Is there a minimum?
The minimum top-up is $10 (3,000 credits). You can buy a preset pack ($10 = 3,000 credits, $20 = 6,000, $50 = 15,000, or $100 = 30,000) or a custom amount, and there is no subscription or monthly commitment — you only spend the credits you buy. You can pay in your local currency at rounded parity (a $20 pack shows as €20 / £20 / CHF 20), with credits granted at the USD-parity value.
What happens when I run out of credits?
Billable calls return HTTP 402 payment_required until you top up your credit balance in the dashboard → Billing. To avoid interruption, turn on auto-recharge: when your credit balance drops below a threshold you set, we automatically add a fixed amount (e.g. $100 = 30,000 credits) using your saved card.
Ready when you are
Put AI in production — without giving up your data.
One private cloud for the models you already use. PHI stays in your region, we never train on or store your data, and every call is yours alone.
Free route checks · Prepaid credits · No data retained