BYOK AI GATEWAY

Ship AI features without shipping your API keys.

Your app embeds a partial key — never your real OpenAI or Anthropic key. HyperProxy reconstructs the real key in memory with split-key encryption, injects it, and streams the response straight back. A database breach or a reverse-engineered binary gets an attacker nothing.

11 providers · iOS · Android · Web · React Native · Flutter · self-host or managed

~/hyperproxy — zsh
$ curl -N https://api.hyperproxyai.com/ab12cd34ef56aa77/c4bc1015a291/v1/chat/completions \
  -H "X-HyperProxy-Key: hp_live_ab12cd34ef56aa77.<key_id>.<client_half>" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o-mini","stream":true,"messages":[{"role":"user","content":"hi"}]}'
data: {"choices":[{"delta":{"content":"Hi!"}}]}
Hi! How can I help?
HOW IT WORKS

Three moving parts. One useless-until-fused key.

Split-key envelope encryption in three synced steps — the real key exists only for the microseconds of a request.

01

Embed a partial key.

Your app ships hp_live_… — a named partial key, not your provider key. Rotate, segment, or revoke it per app version without ever re-entering the real key.

02

Send the service's own request.

Build your upstream's native request — a built-in AI provider or any HTTP API you've added — and POST it to that service's URL, with the upstream's own path appended. No SDK, no wrapper, no lock-in.

03

We fuse the key in memory and stream back.

The real key is reconstructed only at request time, in memory, injected upstream, and the SSE response streams straight back. Wrong half → 401.

client_halfserver_half = data_key

SECURITY

Break it yourself. It won't break.

Split-key envelope encryption means neither half is worth stealing. Try it — drag the two halves together, or leak them one at a time.

Reconstruct it yourself

Drag client_half and server_half onto each other.

drop
to fuse
client_half
in app
server_half
encrypted
result: two useless halves

Steal what's stored. Steal the binary.

Arm a threat and see what an attacker actually gets.

ciphertext =
server_half =
USELESS WITHOUT THE CLIENT HALF
client_half =
USELESS WITHOUT THE SERVER HALF
⊕ both halves present → data_key reconstructed. This only ever happens in memory, at request time.

DB breach = ciphertext + server_half = useless.   Reverse-engineered app = client_half = useless.  The real key never ships in your binary and is never stored in the clear.

App Attest device attestation

Verify requests come from your real app on a real device. App Attest with Secure Enclave signatures, a replay guard (sign_count must strictly increase), and modes off / device_token / assertion — plus a rotatable simulator bypass token for dev. Play Integrity is on the roadmap.

INTEGRATION

This is the whole integration.

Point any request at HyperProxy and swap the auth header. That's it — the body stays your service's own.

request.sh
$ curl -N https://api.hyperproxyai.com/ab12cd34ef56aa77/c4bc1015a291/v1/chat/completions \
  -H "X-HyperProxy-Key: hp_live_ab12cd34ef56aa77.<key_id>.<client_half>" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o-mini","stream":true,"messages":[{"role":"user","content":"hi"}]}'

Copy your service URL from the dashboard and append the upstream's own path: api.hyperproxyai.com/<project>/<service>/<your upstream path>. The URL says where to route; the partial key in the header is the credential — it carries the client half we fuse the real key from. Change the auth header; the body stays byte-for-byte. Any HTTP API, AI or not.

REACH

Every major provider — or any API you add.

Start from a built-in preset, or register any HTTP API by its base URL — an AI model or any other service. Provider-native transit means no SDK lock-in: send each service's own request format and we forward it verbatim, with per-service endpoint allowlists and attestation.

OpenAI
Anthropic
Google Gemini
xAI Grok
DeepSeek
Mistral
Perplexity
Novita
Z.ai
Stability AI
Black Forest Labs
+ any custom API
iOS Android Web React Native Flutter
THE DIFFERENTIATOR

Not just request counts. Tokens and dollars.

Most gateways stop at request counts. HyperProxy meters every request plus input/output tokens plus $ cost, against a hybrid pricing catalog — full usage analytics without leaving your gateway.

▮ hyperproxy · live usage — proj_7d510b9056f3319f
REQUESTS
0
TOKENS
0
COST (USD)
$0.00
gpt-4o-mini$486
claude-sonnet$402
gemini-2.0$221
deepseek-chat$178

Don't just count requests — see what they actually cost, per model and per project, in real dollars.

WHY HYPERPROXY

Built to hide keys in production — not just in a demo.

Ships everywhere

Provider-native transit runs from iOS, Android, web, React Native, or Flutter — no SDK to adopt, no lock-in.

Defense in depth

Split-key envelope encryption plus App Attest device attestation — a database breach or a cracked binary gets an attacker nothing.

Cost you can see

Every request metered by tokens and real dollars, not just a count — full usage analytics without leaving your gateway.

Yours to run

Self-host the open gateway (FastAPI + Postgres + Redis) or let us run it fully managed. Your keys, your data plane.

CAPABILITIES

Everything a gateway should ship with.

Split-key envelope encryption

client_halfserver_half = data_key, reconstructed in memory only.

App Attest device attestation

off / device_token / assertion; Secure Enclave; replay guard; simulator bypass.

Named partial keys

Many per service — rotate, segment, revoke per app version without re-entering the provider key.

Endpoint allowlists

Restrict which upstream paths a key can reach, per service.

Rate-limit rules

Token Bucket, Redis-backed. Scope per key / IP / device; 429 + Retry-After.

Email alerts

Fire after N consecutive upstream failures — know before your users do.

First-class SSE streaming

Token-by-token streaming forwarded straight through, no buffering.

Self-host or managed

FastAPI + Postgres + Redis on your infra, or fully managed by us.

PRICING

Monthly requests. Six tiers. Self-host free.

100,000
requests / month · Pro
Free
$0
1,000 req
Starter
$10
10,000 req
Pro
$50
100,000 req
popular
Premium
$200
1,000,000 req
Business
$2,000
10,000,000 req
Enterprise
custom
unlimited

Plans are monthly request-count. Self-hosting the open gateway (FastAPI + Postgres + Redis) is free — you pay for managed convenience and scale.

DEPLOY

Run it yours, or let us run it.

SELF-HOST

Your infra, your keys.

Clone the gateway. FastAPI + Postgres + Redis. Your data plane, your keys, your control. Free forever.

View the repo
MANAGED

Skip the ops.

We run the gateway, you get a partial key in two minutes. Free tier included, scale when you need it.

$ start free
GET STARTED

Get your partial key in two minutes.

Ship AI features without shipping your API keys.

$ start free

Free tier: 1,000 requests / month. No card required.