Z.ai: GLM 5.3 Flash

Pearl Research states that it retains operational metadata for security and does not train on customer data. No public contractual zero-data-retention terms are linked, so TrustedRouter classifies these routes as Standard and excludes them from ZDR, confidential-compute, and E2EE routing.

Provider policy source

Headquarters / registered office: Tel Aviv-Yafo, Israel.

Company location source (reviewed 2026-09-27).

Inference: Multi-region provider: US Central, Taiwan and Australia declared; model-specific inference location and exhaustive failover scope unconfirmed.

Pearl supplied these serving regions in its marketplace application. This is provider-wide information, not a confirmed per-model or exhaustive failover list. GLM 5.3 Flash and DeepSeek V4.1 Flash do not declare regions in the reviewed native catalog.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-26.

Native model catalog (authentication required)

Privacy policy (not a GPU-location declaration)

Full location evidence

Sail's public DPA and security documentation provide default ZDR for inference: Sail and its subprocessors process prompts and outputs ephemerally in memory, without persistent storage or training absent written consent. Files API uploads and stateful Sailboxes are excluded. This is policy-backed ZDR, not verified confidential compute or E2EE.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Global, dynamically placed; TrustedRouter does not enforce Sail's US-only option.

Sail documents multi-region processing by default, including outside the United States.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-10-28.

Data processing and residency

Provider US-only option

Full location evidence

Boundless's October 27 terms prohibit persistent input/output storage after real-time processing, while retaining content-free request records for up to 90 days. The terms still disclaim third-party infrastructure practices; an equivalent downstream retention commitment is not verified. Routes remain outside strict ZDR, confidential compute and E2EE.

Provider policy source

Headquarters / registered office: Not verified.

Inference: US, UK and/or EU infrastructure, provider-declared; no per-request residency commitment.

October 27 terms, section 3.3, describe provider-wide infrastructure in the US, UK and/or EU; not an exact-model placement receipt.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-10-28.

Infrastructure and data terms

Full location evidence

Inceptron documents zero retention by default: API prompts and outputs are processed transiently and discarded after processing.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Engy's October 21 policy distinguishes its no-content-logging gateway from independent GPU workers. End-to-end ZDR requires provider.zdr=true or a verified account/key setting; TrustedRouter has not verified that setting for this route. Requests without it may reach independently operated workers. Integrity audits may retain output token IDs on qwen3.6-35b-a3b for 30 days. These routes are not strict ZDR, confidential inference or verified E2EE.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference countries undisclosed; no verified country-specific residency commitment.

Qwen3.8-27B and GLM 5.3 Flash are listed as Engy-operated ZDR models, but the reviewed catalog, docs and privacy policy do not disclose their GPU countries or a complete failover-location set.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-26.

API documentation

Privacy and processing path

Full location evidence

Telnyx's published policy states zero data retention for Telnyx-hosted /v2/ai/openai/chat/completions and /v2/ai/openai/embeddings: content is processed in memory and discarded after the response; request metadata is retained. TrustedRouter currently publishes hosted chat routes and adapts Responses to chat completions. Stateful Responses, AI Assistants with conversation history, third-party models and /v2/ai/embeddings are outside this ZDR scope. OpenAI-compatible embeddings may run in any region. DPA 3.1 restricts training of models available to others, with exceptions for written opt-in or data de-identified under 3.5. This is policy-backed ZDR, not confidential compute or verified end-to-end attestation.

Provider policy source

Headquarters / registered office: Austin, Texas, United States.

Company location source (reviewed 2026-09-27).

Inference: Multi-region, dynamically routed among the model's available Telnyx regions; no fixed inference-region commitment on this TrustedRouter route.

Provider-wide GPU region set. Model availability is narrower; see the catalog snapshot below. Germany in the storage-locality documentation does not establish Germany as the inference country.

Region pinning through TR: Not supported by the current TrustedRouter integration: it uses api.telnyx.com without Telnyx's strict region controls. Do not send Telnyx-specific region/mode fields as a TrustedRouter pin.

Reviewed 2026-09-26.

Inference regions and strict pinning

Processing versus storage

Native model catalog (authentication required)

Full location evidence

Makora's Developer Pro and pay-as-you-go tiers advertise ZDR, but permit encrypted on-host SSD caches with no fixed deletion deadline and retention of flagged content for safety investigations. Starter and Developer tiers retain content for 30 days. No training on any tier. These routes remain excluded from strict ZDR.

Provider policy source

Headquarters / registered office: Not verified.

Inference: United States primary processing, provider-declared; international processing is permitted and exact-model residency is unverified.

Privacy policy section 7 lists AWS and TensorWave inference compute in the US; section 10 also permits international processing.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-10-28.

Inference subprocessors and processing region

Full location evidence

Greenference SAS's DPA commits to EU-only inference, no persistent prompt/output storage and no training or secondary use. Shared prefix caches remain in volatile GPU memory until eviction or instance restart; they are not account-isolated and have no fixed maximum lifetime. Content-free operational metadata is retained. Greenference runs its own serving software on rented EU compute; this is contractual ZDR, not verified confidential compute or E2EE. Its current electricity mix is unverified, not a 100% renewable-energy commitment.

Provider policy source

Headquarters / registered office: Not verified.

Inference: EU-only inference, dynamically placed; no individual-country commitment.

All inference is on Greenference-operated serving software on rented EU GPU capacity.

Region pinning through TR: Select provider.only=[greenference] with allow_fallbacks=false to restrict this route.

Reviewed 2026-10-09.

EU processing and retention commitments

Compute subprocessors

Full location evidence

Arcee's July 24 privacy policy permits collection of inputs and outputs to provide and improve its services. No route-specific ZDR exception is verified for TrustedRouter's account. These routes remain Standard, not confidential compute or E2EE.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Atlas Cloud publishes a platform zero-retention policy, while its aggregated model routes can involve downstream providers. TrustedRouter keeps the public route tier conservative pending downstream-path contractual verification.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Baseten states that it does not store synchronous Model API inputs or outputs by default. TrustedRouter uses the synchronous Model API path; Baseten documents separate temporary input storage for async inference.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Direct BytePlus ModelArk inference. Availability and standard token prices are refreshed from BytePlus's native catalog and pricing documentation. Video availability requires a verified native adapter.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Workers AI documents no input/output retention after ordinary stateless inference and no model training. Stateful features, customer-enabled logging/caching, and safety, security or legal exceptions may retain content. No exception-free commitment is verified for this account; these routes remain outside strict ZDR.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

No provider-ZDR claim is tracked here. Crusoe's Managed Inference docs and pricing/catalog pages are linked for model and API data-handling review.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Tracked as no-store, not strict ZDR. DeepInfra documents memory-only handling and no training for ordinary inference, but reserves the right to log a small portion of requests for debugging or security. Google- and Anthropic-backed routes also inherit those vendors' terms.

Provider policy source

Headquarters / registered office: Palo Alto, California, United States.

Company location source (reviewed 2026-09-27).

Inference: US infrastructure plus announced Canadian capacity; model-specific residency unconfirmed.

DeepInfra describes US infrastructure and announced its first international data center in Toronto on July 8, 2026. This is a provider footprint, not an exhaustive or model-specific placement list. DeepSeek V4.1 Flash placement has not been confirmed; do not declare this route US-only.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-27.

DeepInfra infrastructure statement

DeepInfra Toronto announcement

Full location evidence

Featherless's published privacy policy states that prompts and completions are neither collected nor stored. Account, payment and usage metadata, including token counts and sampler settings, may be retained. This is policy-backed ZDR, not verified confidential compute or E2EE.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

No provider-ZDR claim is tracked here. Fireworks publishes security, privacy, and zero-retention documentation; enable a contracted ZDR posture before marking this provider as ZDR.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

No provider-ZDR claim is tracked here. Friendli's legal/privacy terms are linked for users who need to review API data handling.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Marked ZDR via TrustedRouter's arrangement — Nebius RETAINS inputs/outputs by default (for speculative decoding); zero retention is an opt-in control, which the deployed Nebius account has enabled. Nebius does not train on customer data.

Provider policy source

Headquarters / registered office: Amsterdam, Netherlands.

Company location source (reviewed 2026-10-28).

Inference: Global, dynamically placed public inference; no fixed-country commitment.

Token Factory public endpoints are Global; Finland storage of retained content does not identify the inference location.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-10-28.

Processing and dedicated endpoint residency

Full location evidence

No provider-ZDR claim is tracked here. Novita's privacy policy says personal information is not used for model training; customer-content processing is governed by customer agreements.

Provider policy source

Headquarters / registered office: San Francisco, California, United States.

Company location source (reviewed 2026-09-27).

Inference: Shared inference API; processing countries unconfirmed, no fixed-region commitment.

No exhaustive inference-country list verified for the shared model API. Novita publishes worldwide GPU rental regions, but that separate product does not establish shared serverless model placement.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-10-28.

GPU rental regions (different product)

Native model catalog

Full location evidence

Tracked as ZDR for serverless and dedicated inference. Parasail documents no storage or logging of submitted input on those service paths, retention only while generating and delivering output, and no training on input or output. Batch service is excluded from this claim; TrustedRouter does not route Parasail traffic through batch.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

No provider-ZDR claim is tracked here. SiliconFlow's privacy policy source is linked for retention and interaction-data terms.

Provider policy source

Headquarters / registered office: Singapore (international API operator).

Company location source (reviewed 2026-09-27).

Inference: Inference countries unconfirmed; no verified country-specific residency commitment.

TrustedRouter uses api.siliconflow.com. Neither its hostname nor the provider's Singapore legal jurisdiction establishes the DeepSeek V4.1 Flash GPU location. No exhaustive route-specific country list verified.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-26.

API documentation

Privacy policy (not a GPU-location declaration)

Full location evidence

No provider-ZDR claim is tracked. StreamLake's public privacy policy is linked for API data-handling review.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

TokenHub's Singapore API uses global resource scheduling, not a Singapore-only inference guarantee. Only canaried chat routes with matching regional USD prices are enabled. No verified contractual ZDR, confidential-compute, or upstream E2EE claim is tracked.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Global, dynamically scheduled inference; no fixed-country residency commitment.

The Singapore TokenHub ingress uses global resource scheduling. Ingress location is not GPU residency.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-29.

API regions and resource scheduling scope

Full location evidence

Tracked as provider ZDR. Together documents that inference inputs and outputs are not stored by default; temporary prompt caching may be used for performance, and sharing content for training is opt-in.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Wafer's authenticated model catalog reports that this exact route supports request-scoped ZDR via Wafer-ZDR: required.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

W&B Serverless Inference runs on CoreWeave infrastructure. W&B does not publish a zero-retention, confidential-compute, or end-to-end-encryption commitment for this service, so these routes use the Standard privacy tier. TrustedRouter does not enable W&B Weave tracing for provider calls.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

No provider-ZDR claim is tracked here. Z.AI/BigModel policy source is linked for users who need to review API retention and processing terms.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Zro declares no retention of prompts, outputs or request bodies and no training or secondary use without separate consent, including by its infrastructure providers. Short-lived, account-scoped prompt caches and content-free operational metadata remain. This is provider-declared ZDR, not independently verified confidential compute or E2EE.

Provider policy source

Headquarters / registered office: Not verified.

Inference: Europe or United States; no fixed-country or per-request residency commitment on this route.

Provider-declared inference locations, including third-party capacity. Authentication is routed through the EU.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-10-11.

Inference placement and key restrictions

Full location evidence

Lyceum's terms state that inference inputs and outputs are used only to generate results, are not stored beyond technical necessity, and are not used for training or analysis. No account-specific ZDR or verified confidential-compute guarantee is tracked; these routes remain Standard. German company jurisdiction is not a guarantee that every model executes in the EU.

Provider policy source

Headquarters / registered office: Berlin, Germany; Zurich, Switzerland (registered offices).

Company location source (reviewed 2026-10-28).

Inference: Inference location not verified; no country-specific residency commitment.

Lyceum documents model-specific serving locations; its German headquarters is not a fleet-wide EU residency guarantee.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-30.

Model-specific hosting and pricing

Full location evidence

In its September 28, 2026 marketplace submission, io.net states that inference prompts and completions are processed only in memory, are not stored or logged, and are not used for training. Content-free operational metadata is retained for billing, capacity planning and abuse prevention. This is a provider declaration: the reviewed public privacy policy does not establish inference-specific zero-retention terms, and the applicable DPA has not been reviewed. Routes remain Standard pending that evidence. Confidential compute is offered on request, but this integration has no verified confidential-compute or provider-side E2EE guarantee.

Provider policy source

Headquarters / registered office: West Hollywood, California, United States (operating address).

Company location source (reviewed 2026-09-28).

Inference: United States and Canada, provider-declared; no US-only or fixed-country guarantee on this route.

io.net declares US and Canadian serving locations and data residency in its September 28, 2026 marketplace submission. This is provider-wide information, not an independently verified per-model or per-request location.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-28.

API documentation (not a location guarantee)

Privacy policy (operator identity, not GPU residency)

Full location evidence

Requests and responses are encrypted between TrustedRouter's enclave and release-pinned Privatemode workloads after attestation verification. Verification failures reject the request; there is no plaintext fallback. Privatemode explicitly states that prompts and responses are not stored after a request completes and are not used for training. Transient inference state may remain in a salt-isolated, in-memory prompt cache inside confidential workers until eviction. Operational metadata is retained for up to 90 days; per-key token usage is retained permanently for billing. Cache-routing metadata is visible to the provider edge. ZDR describes prompt/output retention, not metadata.

Provider policy source

Headquarters / registered office: Not verified.

Inference: EU-hosted inference, provider-declared; country and individual worker location unspecified.

Privatemode declares EU hosting for its inference service. This does not establish an individual worker's country.

Region pinning through TR: Not supported by the current TrustedRouter integration.

Reviewed 2026-09-27.

Privatemode EU hosting

Full location evidence