OpenAI compatible API · Attested · Public status

Tinfoil Alternative — Verifiable Privacy, Every Provider

Same verifiable-privacy bet as Tinfoil, applied as a router. Attested, no-log gateway across 30+ providers with one API.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Tinfoil alternative

Same verifiable-privacy bet. TrustedRouter routes across every provider.

Tinfoil pioneered verifiable confidential inference, and the thesis is right: attestation beats a privacy policy. TrustedRouter shares it — and applies it as a router, not a single inference endpoint.

That means you keep model choice. Route the same attested, no-log gateway to Claude, GPT, Gemini, DeepSeek, Kimi, Llama, Mistral and 20+ more, with automatic fallback, one OpenAI-compatible API, and one key.

Compare models in the playground How attestation works

One API, every providerPython

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key="sk-tr-v1-..."
)

# Same attested gateway, any model:
for model in ["anthropic/claude-sonnet-4.6",
              "openai/gpt-5.5",
              "deepseek/deepseek-v4-flash"]:
    client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": "hi"}],
    )

Shared thesis

Verify, don't trust.

Hardware attestation + open source. We agree with Tinfoil on the principle — privacy you can check beats privacy you're promised.

Router, not endpoint

30+ providers, one key.

Don't pick a single confidential model — route the attested gateway to the best model for each job, with fallback when one is down.

Drop-in

OpenAI-compatible.

Change one base_url and keep your existing SDK, model IDs, and code. Migrate an existing OpenRouter or OpenAI integration in minutes.

TinfoilTrustedRouter

AttestationYesYes

Open sourceYesYes

ShapeConfidential inferenceMulti-provider router

Model choiceHosted model set30+ providers, switchable per call

Provider fallbackn/aAutomatic rollover

Best fitA confidential endpoint for chosen modelsVerifiable routing across the whole model market

Same destination, wider road

Attestation should cover the whole market, not one endpoint.

The future where every prompt goes through an attested path shouldn't require giving up model choice. TrustedRouter is the bet that you can have both: verifiable privacy and the full provider market behind one API.

The argument in full: “Attestation is All You Need”.

Live catalog evidence

Current routes, prices, privacy, and measured performance.

Catalog facts come from the routes currently configured in TrustedRouter. Performance uses the same cached metadata snapshot as the public leaderboard. Prompts and outputs are not part of these measurements.

554public models

95providers

1761configured routes

314ZDR routes

35provider E2EE routes

5539recent availability samples

Model	Providers	Context	Input	Output	Privacy	Measured route
DeepSeek: DeepSeek V4.1 Flash`deepseek/deepseek-v4.1-flash`	+10 23 routes	1,048,576	$0.0422/1M to $0.68575/1M	$0.0844/1M to $1.52975/1M	E2EE	3830 ms TTFT deepinfra · 100.00% available · n=483
DeepSeek: DeepSeek V4 Flash 0731`deepseek/deepseek-v4-flash-0731`	+21 33 routes	1,048,576	$0.047475/1M to $2.11/1M	$0.09495/1M to $10.55/1M	confidential	3028 ms TTFT deepinfra · 32 tok/s · 99.25% available · n=303
DeepSeek V4 Pro 0813`deepseek/deepseek-v4-pro-0813`	2 routes	1,048,576	$1.3926/1M	$4.1778/1M	ZDR	1221 ms TTFT baseten · 139 tok/s · 98.55% available · n=277
GLM 5.2 Fast on Fireworks`z-ai/glm-5.2-fast`	4 routes	1,048,576	$2.2155/1M	$6.963/1M	ZDR	3050 ms TTFT fireworks · 153 tok/s · 100.00% available · n=171
Z.ai: GLM 5.2`z-ai/glm-5.2`	+24 44 routes	1,048,576	$0.7174/1M to $2.434307/1M	$1.5825/1M to $7.029062/1M	E2EE 4 cited scores	1806 ms TTFT baseten · 128 tok/s · 100.00% available · n=145
Z.ai: GLM 5.3 Flash`z-ai/glm-5.3-flash`	+23 41 routes	1,048,576	$0.07385/1M to $2.11/1M	$0.2532/1M to $10.55/1M	E2EE	8850 ms TTFT zai · 100.00% available · n=128