OpenAI compatible API · Attested · Public status

Qwen, GLM, Kimi & DeepSeek APIs Hosted on US Infrastructure

Use Qwen, GLM, Kimi, and DeepSeek through US-hosted attested infrastructure. Prompts never reach the model vendor, and you can verify that live.

Verify gateway

Onebase URL to migrate

100sof models and routes

Noneprompt logs by default

Qwen, GLM, Kimi and DeepSeek without the vendor endpoint

Run GLM, Qwen, Kimi, and DeepSeek on US-hosted, attested infrastructure that never forwards a prompt to the model vendor.

Your benchmarks already picked these models. GLM-5.2, Qwen 3.5, Kimi K2.7, and DeepSeek V4 Pro all run as routes here, alongside MiniMax M3. Then legal asks where the API traffic goes. A vendor-hosted endpoint sends every prompt to the model vendor's servers, and self-hosting the weights means running your own GPUs.

There is a middle path. TrustedRouter serves the same open weights via non-Chinese hosting providers inside a hardware-attested confidential-compute gateway, with Zero-Data-Retention and TEE tiers per route. TrustedRouter does not store prompt or output content by default. The API is OpenAI-compatible, and EU-focused routing is available.

Browse the model routes Verify the attestation

glm_us_hosted.pyPython

from openai import OpenAI

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

reply = client.chat.completions.create(
    model="glm-5.2",  # also: qwen-3.5, kimi-k2.7,
                      # deepseek-v4-pro
    messages=[{"role": "user",
               "content": "Refactor this handler."}],
)

Routing

Prompts skip the vendor

DeepSeek, Kimi, Qwen, GLM, and MiniMax routes run on attested infrastructure operated by non-Chinese hosting providers. On the TEE tier, end-to-end confidential compute means even the hosting provider cannot read your prompt. Kimi users can start at the dedicated Kimi K2 API page.

Verification

Check it live, per session

The gateway source is open, the image digest is published, and the attestation endpoint returns a JWT signed by the CPU vendor's root key, bound to your live TLS session. Attestation beats a privacy policy. Details and the curl command are on the security page.

Scope

Hosting fixes residency

Routing changes where your data goes. The labs that trained these weights stay the same, so judge the models on quality like any other route. Your prompts stay on attested infrastructure you can verify, without renting GPUs to self-host.

Vendor-hosted API (z.ai, Moonshot, Alibaba)TrustedRouter

Model accessDirect from the lab that trained the model220+ routes across 30+ providers behind one API

Where prompts goThe vendor's own serversNon-Chinese attested hosts; prompts never reach the vendor

RetentionSet by each vendor's policyNo prompt or output content stored by default; ZDR routes contractually keep nothing

VerificationA privacy policy you read and trustLive attestation: a CPU-vendor-signed JWT bound to your TLS session

Sensitive questionsGLM answered 30 of 60 on our test setSame weights answered 60 of 60 through the enclave

PricingFirst-party list pricesThin markup over provider list prices; see pricing

Host-applied filtering, measured

Same weights, different host, different answers.

We ran 60 sensitive questions against the same GLM weights through two doors. The vendor-hosted API answered 30 of 60. TrustedRouter's attested enclave answered 60 of 60. That filtering is host-applied: it lives in the serving stack rather than in the weights you benchmarked.

Where a model is hosted decides what leaves your building and what comes back. Privacy you can check beats privacy you're promised. A document-processing company scaled from zero to over a billion tokens per week through the attested gateway within three weeks of onboarding. Pick a route in the model chooser, or open the playground and test your own prompts against a US-hosted GLM, Qwen, Kimi, or DeepSeek route right now.

Questions

Do my prompts go to China when I use Qwen, GLM, or Kimi through TrustedRouter?

No. DeepSeek, Kimi, Qwen, GLM, and MiniMax routes are served via non-Chinese hosting providers on attested infrastructure, and prompts do not go to the model vendor. Zero-Data-Retention and TEE tiers are available per route; on the TEE tier, end-to-end confidential compute means even the hosting provider cannot read your prompt. You can verify the gateway live through the attestation endpoint described on the security page.

Is the GLM served through TrustedRouter the same model as the vendor-hosted API?

Same open weights, different serving stack. We measured one difference: the same GLM weights answered 60 of 60 sensitive test questions through TrustedRouter's enclave versus 30 of 60 through the vendor-hosted API. That filtering is host-applied rather than baked into the weights. Try your own prompts against the route in the playground and compare the answers for yourself.

Do I need to change my code to switch from a vendor-hosted endpoint?

The API is OpenAI-compatible. Change the base URL, keep your SDK, model ids, and code, and pick a route from the model catalog. Automatic provider fallback rolls requests over when a provider is down. You can pay with prepaid credits, bring your own provider key, or use x402 pay-per-request with MetaMask wallet sign-in.

Can my compliance team use this for regulated data?

TrustedRouter publishes SOC 2 readiness and HIPAA readiness documentation, plus a DPA, a BAA, and a subprocessor list. These are readiness materials, not audit reports or certifications: verifiable architecture plus documentation your compliance team can assess. The open-source gateway, published image digest, and live attestation give reviewers something to check directly rather than a questionnaire answer to file.