TrustedRouter | End-to-End Encrypted Router for AI

Production AI now needs an inference control layer.

Most AI products start by calling one model provider directly. That works until you need fallback, model choice, cost control, regional routing, privacy controls, provider-specific policies, customer trust, or proof that sensitive prompts are not being logged by another intermediary.

Providers fail or rate-limit

Model quality changes

Costs move by workload

Sensitive prompts create trust risk

Closed routers create another vendor to trust

Customers increasingly ask where their data goes

Move over with one base_url change.

• ✓ Use trustedrouter/auto for fallback
• ✓ Use trustedrouter/eu with the EU regional API for Europe-focused routing
• ✓ Use provider.data_collection = "deny" for zero-retention provider preference
• ✓ Use BYOK where needed
• ✓ Keep existing OpenAI-shaped calls working

View migration guide →

Drop-in, OpenAI-compatibleTypeScript

const client = new OpenAI({
  apiKey: process.env.TRUSTEDROUTER_API_KEY,
  baseURL: "https://api.trustedrouter.com/v1"
})

const response = await client.chat.completions.create({
  model: "trustedrouter/auto",
  messages: [{ role: "user", content: "Hello" }],
  provider: { data_collection: "deny" }
})

Your prompt path should be inspectable.

TrustedRouter separates production inference from the normal dashboard/control-plane surface. Prompt and output bodies should not pass through the control plane. Metadata is used for billing, routing, latency, status, and cost tracking.

Fallback when providers fail.

Production AI should not break because one provider returns 429s, 5xx errors, degraded latency, or temporary capacity issues. TrustedRouter routes across healthy providers and exposes route health so teams can build more resilient AI products.

View status

Router availability99.99%

Live regions3

Provider health Healthy

Median routing overhead8ms

Privacy is not a setting buried in a dashboard.

For sensitive AI products, the question is not only which model you use. It is who can see the prompts, what gets logged, which providers retain data, and whether the router itself can be inspected.

FeatureDirect Provider APIClosed RouterTrustedRouter

One API across providersNoYesYes

Provider fallbackNoYesYes

BYOK supportSometimesSometimesYes

Zero-retention preferenceVariesUnknownYes

Prompt/output logsYes (API dependent)Yes (usually)Never

Open-source routerN/ANoYes

Public attestationN/ANoYes

Customer-facing trust recordN/ANoYes

Model	Maker	Context	Prompt price	Class
qwen/qwen3-235b-a22b-2507	Alibaba	262k	$0.11 / 1M	Open weights
z-ai/glm-5	Zhipu AI	205k	$0.66 / 1M	Open weights
deepseek/deepseek-v4-flash	DeepSeek	1M	$0.14 / 1M	Open weights
google/gemma-4-31b-it	Google	262k	$0.14 / 1M	Open weights
moonshotai/kimi-k2-thinking	Moonshot	262k	$0.66 / 1M	Open weights
trustedrouter/eu	EU-focused	Varies	Varies	Regional
trustedrouter/auto	Multiple (failover)	Varies	Varies	Attested + ZDR
anthropic/claude-sonnet-4.5	Anthropic	200k	$3.00 / 1M	Frontier

Usage-based routing. No subscription required.

Start with prepaid credits, BYOK, or usage-based billing. Teams already spending on LLMs can request migration credits.

What is TrustedRouter?

A privacy-first AI gateway that routes LLM requests across multiple providers (OpenAI, Anthropic, Google, and more) through a single OpenAI-compatible API, without logging prompts or outputs.

Is this an OpenRouter alternative?

Yes, but with different design constraints. We prioritize production infrastructure, privacy, and verifiable trust. See our OpenRouter comparison for details.

Do you log prompts or outputs?

No. Never. The prompt payload passes through an attested gateway and is intentionally excluded from our control plane and metadata systems.

What does "attested gateway" mean?

Our routing layer runs inside a Trusted Execution Environment. We publish cryptographic attestations that the running code exactly matches the open-source repository — so even our own engineers cannot read your requests.

What metadata do you store?

Only what billing and routing need: request timestamp, routing duration, target model, HTTP status, API key reference, and token counts. No prompt text or message arrays are evaluated by the control plane.

Can I bring my own provider keys (BYOK)?

Yes. BYOK lets you use existing committed spend or enterprise rate limits while gaining the latency and privacy benefits of the TrustedRouter architecture.

What happens if attestation fails?

The gateway fails closed. It refuses to serve traffic rather than fall back to an unverified routing state.

How do I migrate from OpenRouter?

It is a one-line change. Swap your base_url and keep your API calls the same. See the migration guide.