Pricing.

Three flat rates. No subscription tiers. No minimums. No per-seat charges. You pay markup on top of provider cost — and that's the whole story.

Mode
Markup
Why this rate
CloakAPI keyspooled provider keys, prompt-pool privacy
15 %
We hold the provider keys and your prompts pool with everyone else's, so providers see "a CloakAPI call" not "you". Highest privacy at the upstream layer.
BYOKbring your own provider keys
5 %
You hold the provider keys; we tokenise + route + sign receipts. The provider bills you directly. We add 5% on top, billed by us.
Complete-localdesktop runs the model
5 %
Self-hosted Ollama / llama.cpp / desktop bundle. Zero round-trips to a cloud provider. We add 5% on the local token count for the receipt + audit trail.
Switch any time · per API key · operator can pin to one mode Start free Quickstart

What it costs you.

Pick a mode + model + monthly token volume. The numbers below are all live; we maintain the price book at docs/pricing/price-book.json.

Provider cost (blended at 1 : 4 input:output — adjust below)
$115.90
CloakAPI markup
$17.39
Total / month
$133.29
Per million tokens
$13.33

Per-model token prices.

Provider list prices in USD. Local models bill against a cloud-equivalent basis at 5% markup. Move the slider to see how the typical-chat blended rate moves with your input/output ratio.

1 : 4
Model Input / 1M Output / 1M Typical chat / 1M
Anthropic · Claude Opus 4.8 $5.00 $25.00
Anthropic · Claude Sonnet 5 $3.00 $15.00
OpenAI · GPT-5.5 $5.00 $30.00
OpenAI · GPT-5.4 $2.50 $15.00
xAI · Grok 4.3 $1.25 $2.50
Google · Gemini 3.5 Flash $1.50 $9.00
DeepSeek · V4 Flash $0.14 $0.28
Local · Llama 3.2 8B (Ollama, 16+ GB VRAM) $0.00 (own GPU) $0.00 (own GPU)
Local · Llama 3 70B (Ollama, 80 GB VRAM) $0.00 (own GPU) $0.00 (own GPU)
Local · Qwen 2.5 7B (Ollama, 16+ GB VRAM) $0.00 (own GPU) $0.00 (own GPU)

Prices in cents per 1M tokens stored as data-in / data-out. "Typical chat" = blended rate at the selected ratio (default 1 : 4 — 1 input token per 4 output tokens — matching most assistant-style traffic). Local rows show the 5% CloakAPI markup against a cloud-equivalent basis, since the model itself runs free on your hardware.

What you get at every rate.

No tier comparison columns. There aren't any. Every account gets all of these.

Token-level redaction at your edge — 13 PII entity types (growing)
Chain-linked, ECDSA-P-256 signed receipts on every call
Failed-call attestation receipts (4xx + 5xx)
Public receipt verifier — your auditor needs no CloakAPI account
Every provider — Anthropic, OpenAI, Google Gemini, xAI Grok, DeepSeek + self-hosted local (Ollama / LocalAI). Bring your own key for OpenRouter, Perplexity, Mistral & many more.
Outbound webhooks (HMAC-SHA256, retry policy, replay)
Compliance packs — HIPAA, GDPR, PCI DSS 4.0, FINRA, NHS DSPT
EU hosting (Hetzner Nuremberg) — for receipt-signing, billing, and staff audit logs only. On the client-side ways (desktop, browser extension, local proxy) and the chat, tokenisation runs on your device before egress, so raw prompts never reach us; the gateway is a blind token relay that never tokenises on our servers — to tokenise with a plain SDK, point it at the local proxy so it happens on your own machine.
FIPS-validated path via aws-lc-rs CMVP #4759

How this differs.

Every privacy-preserving AI gateway promises to handle your data carefully. CloakAPI promises something stronger. On the client-side ways — desktop app, browser extension, local proxy, and the chat, which tokenises in your own browser — we never see your plaintext PII at all: tokenisation runs on your device before any byte leaves it, so the math says we can't read your prompts even if we wanted to, and that fact is itself attested in every receipt. Our gateway is a blind token relay — it forwards only the tokens your device produced and never inspects, detects, or tokenises content on our servers. It never tokenises on our servers, so to protect a plain SDK you point it at the local proxy and tokenisation stays on your own machine. We never hold your plaintext — which is why many customers conclude that, on those paths, we aren't a Business Associate, Processor, or Service Provider the way a gateway that stores plaintext is (a structural argument to evaluate with your own counsel — not legal advice).

Every reply ships with a chain-linked, ECDSA-P-256-signed receipt envelope. Any auditor can verify it offline against our public JWKS at signedreceipts.org/verifier — no CloakAPI account, no cooperation from us required. We don't know of a competing gateway that publishes this artifact today. It's the thing that ends "is this provider trustworthy" conversations, because the answer stops depending on trust.

Our markup is structural — we have to make money per call — but it's flat: 15% on pooled keys, 5% on BYOK, 5% on local. There is no "Enterprise" tier that unlocks SSO, audit logs, BAA, or compliance packs. Every API key gets every feature, on day one, at the same rate.

$2 trial credit on signup · No credit card · No expiry

Pricing FAQ.

Why three rates instead of one?
The rate reflects the work we do per call. CloakAPI keys = we cover the provider relationship + key rotation + suppression list (15%). BYOK = you hold the keys, we just route + tokenise + receipt (5%). Local = no provider at all, we sign the receipt against your local token count (5%).
Are there tiers I'm missing? Free / Pro / Enterprise?
No. Every account gets every feature. We considered tiering compliance packs, named-engineer support, federated benchmarks — and rejected each as gatekeeping. Pricing is structural, not artificial.
Do you charge per seat / per developer?
No. You can have 1 developer or 100; the cost is identical for the same call volume.
What's the minimum spend?
$10 minimum top-up. Auto-top-up is opt-in. Turn it on in billing settings; pick your trigger threshold and top-up amount.
How does auto-top-up work?
Auto-top-up is opt-in and off by default. In billing settings you turn it on, then pick a trigger threshold ($5 / $10 / $25 / $50) and a top-up amount ($10 / $25 / $50 / $100, or match your 7-day average). When your prepaid balance falls below the threshold, we charge your default payment method for the configured amount. You can change the values or switch it off any time.
How does the $2 trial credit work?
Sign up → $2 lands on your prepaid balance immediately. No card on file. Spend it on any provider. When it runs out, your calls 402 until you top up. Nothing auto-charges.
What if a provider raises their prices?
We pass it through immediately. Our markup percentage stays the same. The price book at docs/pricing/price-book.json is source-of-truth and gets a new version every time a provider posts a change; subscribe to its RSS for advance notice.
What about partner / sub-org pricing?
Partners (resellers / MSPs / agencies) get a commission per sub-org call — see the partner signup page for the L1/L2/L3 commission structure. Customers see the standard rates above.