Confidential AI inference · Verified August 16, 2026

TrustedRouter vs Tinfoil

Tinfoil runs open-source models inside hardware enclaves it operates and lets clients cryptographically verify the running code, GPUs, and model weights: attestation that reaches deeper than ours, across roughly a dozen models. TrustedRouter attests its gateway, routes across ~550 models on ~49 providers, and includes Tinfoil itself in its confidential-compute E2E pool.

Compare details
8decision dimensions
7official sources
1base URL to try TR
Choose Tinfoil when

Its operating model is the feature.

Choose Tinfoil when open-source models cover the workload, or you can bring your own weights via Containers, and you want zero retention enforced by enclave hardware on every request, with SOC 2 Type II and verification down to the GPU and model weights.

Choose TrustedRouter when

Privacy needs evidence.

Choose TrustedRouter when you need closed models from Anthropic, OpenAI, and Google alongside open ones — roughly 550 routes across ~49 providers behind one attested gateway — with an opt-in ZDR routing floor (trustedrouter/zdr) and Tinfoil-class enclave routes still reachable via trustedrouter/e2e.

DimensionTinfoilTrustedRouter
DeploymentHosted enclaves it operates: AMD SEV-SNP VMs, NVIDIA Hopper/Blackwell CC GPUsHosted control plane, source-available (BUSL-1.1), with an attested API path
API surfaceOpenAI-compatible API; SDKs verify enclave attestation; EHBP body encryptionOpenAI Chat Completions and Responses plus Anthropic Messages
Model access6 chat models, ~12 total (Aug 2026); open-source only — no GPT-5 or Claude500+ models across ~50 providers: prepaid, BYOK, and direct
RoutingOne attested router load-balancing its own model enclaves; no other providersProvider fallback plus auto, cheap, fast, free, ZDR, E2E, and EU routes with composable privacy and jurisdiction preferences
ObservabilityUsage dashboards, teams, Admin API; no prompt or content logs by designMetadata analytics and opt-in external broadcast
Prompt contentZero retention enforced by enclave architecture, default on every requestNo durable prompt or output logs on realtime inference; batch is opt-in encrypted retention
VerificationClient verifies router enclave; router transitively checks model enclaves, GPUs, weightsLive gateway attestation on three clouds, bound to published source and release evidence
BillingPer-token (GPT-OSS 120B $0.15/$0.60 per 1M); Chat $20/mo; Containers $20/mo + usagePrepaid at provider price + 5.5% ($0.01/M floor), or BYOK

What Tinfoil actually is

Tinfoil Inc. is a San Francisco company, founded in 2024, YC Spring 2025 batch, about five people per its YC profile. It runs open-source models inside hardware secure enclaves it operates: AMD SEV-SNP confidential VMs paired with NVIDIA Hopper and Blackwell GPUs in confidential-compute mode. Since July 2025 every inference request passes through a unified router at inference.tinfoil.sh, itself an attested enclave whose source is public under AGPL-3.0.

Three products. Private Chat is a consumer app at $20/month with a 3M-tokens/hour fair-use cap. The Private Inference API is OpenAI-compatible, billed per token. Tinfoil Containers (GA March 2026) runs any Docker image inside an enclave for $20/month plus usage, with H200 GPUs at $2,000/month and B200 at $5,000/month. As of August 2026 the API catalog is 6 chat models (Kimi K3, GLM-5.2, DeepSeek V4 Flash, Gemma 4 31B, GPT-OSS 120B, Llama 3.3 70B) plus vision, audio, embedding, and safety models, roughly a dozen models total. Open-source models only: Tinfoil's homepage says plainly that closed models like GPT-5 and Claude cannot run there. Containers is the escape hatch: bring your own weights, including proprietary fine-tunes.

Where Tinfoil is genuinely strong

Tinfoil verifies further down the stack than any gateway we compare against, ourselves included. Client SDKs check the router enclave's attestation against measurements published through GitHub and Sigstore; the router then verifies each downstream model enclave, including NVIDIA GPU attestation and model weights on dm-verity read-only volumes checked against Sigstore bundles. The chain proves which code and which weights served a request. Zero retention is architectural and the default on every request; per their security FAQ, prompts and completions live only inside enclaves and are never written to disk or logged. The enclave code is open source (AGPL-3.0), the SDKs Apache-2.0, and the company holds a SOC 2 Type II report covering security, availability, and confidentiality. Pricing is competitive despite confidential-compute overhead: GPT-OSS 120B costs $0.15 input / $0.60 output per million tokens, with prompt-caching discounts since July 2026.

A precision note our earlier page got wrong: the client directly verifies the router enclave only. Model-enclave, GPU, and weight checks happen transitively inside that router; Tinfoil's docs say client SDKs "only need to verify the first enclave in this chain." End-to-end trust therefore rests on the attested router doing the downstream checks. We had described it as client-side verification of everything. Corrected.

How TrustedRouter differs

Depth versus breadth. Tinfoil attests the model runtime. TrustedRouter attests the gateway: api.trustedrouter.com runs a published workload inside a TEE, verifiable live on three clouds (GCP Confidential Space, AWS Nitro Enclaves, Azure Confidential Containers) at trust.trustedrouter.com, with a runnable verifier script. Behind that gateway sit roughly 550 model routes across about 49 providers as of August 2026, including the closed models from Anthropic, OpenAI, and Google that Tinfoil cannot host. Downstream providers are covered by cited policy and contract tiers, not by our attestation. Tinfoil proves more about a narrow catalog; we prove the prompt path into a broad one.

Tinfoil is in our catalog. Tinfoil is one of our upstream providers. The trustedrouter/e2e route (alias confidential) restricts routing to providers running confidential compute with provider-side end-to-end encryption; today that pool is Tinfoil and Phala. The trustedrouter/zdr route enforces a contractual zero-data-retention floor across a wider pool that also includes Anthropic, OpenAI, and Google. One policy can therefore prefer enclave-hosted routes and fall back to policy-ZDR closed models when the open catalog cannot handle a task. Two caveats: on those routes the enclave posture is Tinfoil's or Phala's mechanism, outside our attestation boundary, and through our gateway you do not run Tinfoil's client-side verification.

Logging and pricing bases. Realtime inference keeps no durable prompt or output logs; we retain metadata (request ids, model, token counts, latency, cost, region, API-key hash). Batch is separate and opt-in, with enclave-encrypted retention up to 30 days (privacy). On price, the bases differ, so no single fee comparison is honest: TrustedRouter charges the upstream provider's token price plus 5.5% with a $0.01/M floor (pricing), while Tinfoil sets flat per-token prices for models it hosts itself. Compare final per-million prices on /models against tinfoil.sh/pricing.

What we do not claim

  • Our attestation covers the gateway build, not model providers. On non-E2E routes, downstream zero retention is a contractual or policy claim with cited catalog flags, defaulting conservatively to assume-stored.
  • Our gateway and control plane are source-available under BUSL-1.1, each release converting to Apache-2.0 four years after publication; the SDKs are Apache-2.0 or MIT. Tinfoil's enclave stack is AGPL-3.0 open source, a real difference in their favor. In both products, the security-critical code that touches your prompt is public.
  • We publish no SOC 2 or HIPAA certification today. Tinfoil has SOC 2 Type II; HIPAA in progress per their security FAQ.
  • We are young: public repos since late April 2026, public benchmark reports since June 2026, short on-page uptime history (about 72 hours detailed, plus monthly rollups). Tinfoil was founded in 2024 with about five people. Vendor-risk reviewers should weigh early-stage risk on both sides of this page.

Migration reality

Both APIs are OpenAI-compatible, so moving either direction is a base URL and key change. From Tinfoil to TrustedRouter, three things do not carry over: Tinfoil's client-side enclave verification (our SDKs verify our gateway attestation instead, a narrower check), the EHBP encrypted-body protocol, and Tinfoil model ids such as kimi-k3, which you map to catalog ids or to trustedrouter/e2e to keep enclave-hosted execution. Our only step-by-step migration doc today covers OpenRouter, so plan the id mapping by hand. In the other direction, Tinfoil has no closed models, so Claude or GPT traffic has nowhere to land there. Relevant to either plan: Tinfoil has shipped two breaking API changes since July 2025 (router unification, July 2025; mandatory EHBP, October 2025, SDKs v0.10.0+), and its catalog churns monthly; Kimi K2.6 and DeepSeek V4 Pro were removed in July 2026, with Kimi K3 and DeepSeek V4 Flash added in August. Budget for model-id maintenance either way, and see our security page for what our side lets you verify.

Migration shape

Start with one real request.

Both APIs are OpenAI-compatible: swap the base URL and key. Tinfoil's client-side enclave verification and EHBP body encryption do not carry over, and Tinfoil model ids map by hand to TrustedRouter catalog ids — or to trustedrouter/e2e to keep enclave-hosted execution on Tinfoil or Phala.

Keep the first test small, stream the response, and compare output, latency, provider selection, and billed usage before moving production traffic.

Agent setup Run a small eval

TrustedRouter sideOpenAI SDK
from openai import OpenAI

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

with client.chat.completions.create(
    model="trustedrouter/zdr",
    messages=[{"role": "user", "content": "Reply PONG"}],
    stream=True,
) as response:
    for chunk in response:
        print(chunk.choices[0].delta.content or "", end="")
Official evidence

Sources checked August 16, 2026

Report a change
All gateways

Questions

Is Tinfoil's privacy guarantee stronger than TrustedRouter's?

At the model runtime, yes. Tinfoil executes models inside SEV-SNP enclaves with confidential NVIDIA GPUs and enforces zero retention in hardware by default. TrustedRouter's attestation covers our gateway; downstream zero retention on most routes is a cited contractual or policy claim. Our trustedrouter/e2e route narrows routing to confidential-compute providers (currently Tinfoil and Phala), but those enclaves are the provider's mechanism, not ours. If open-source models fit and the whole path must be hardware-enforced, Tinfoil is the stronger guarantee.

Can I run Claude or GPT-5 on Tinfoil?

No. Tinfoil's homepage states that closed-source models like GPT-5 and Claude cannot run there; as of August 2026 the API catalog is 6 chat models, all open source. Tinfoil Containers does let you run your own weights, including proprietary fine-tunes, in an enclave. TrustedRouter routes to Anthropic, OpenAI, and Google under cited policy ZDR tiers, which is the main reason to put us in front.

Can I reach Tinfoil's enclaves through TrustedRouter?

Yes. Tinfoil is one of our upstream providers, and trustedrouter/e2e restricts routing to Tinfoil and Phala. You get our failover, one API across every provider, and unified billing at provider price + 5.5% with a $0.01/M floor. You give up Tinfoil's client-side verification: through our gateway you verify our attestation, and the Tinfoil-side enclave posture is their published mechanism, outside our attested boundary.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.