OpenAI compatible API · Attested · Public status
Subprocessors
Review platform vendors and downstream model providers used by TrustedRouter, including purpose, data categories, location, retention posture, and policy sources.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Platform vendors9 listed.
Model providers91 listed.
Prompt accessOnly selected downstream model routes receive prompt content.
Downstream model providers are subprocessors only when customer traffic is routed to them. For legal work, use trustedrouter/zdr, trustedrouter/e2e, or a customer-approved provider allowlist.
Platform subprocessors
Vendors used to operate TrustedRouter.
| Name | Purpose | Data access | Policy |
|---|---|---|---|
| Google Cloud Platform | Cloud hosting, Confidential Space, Cloud Run, Spanner, Bigtable, KMS, Secret Manager, and operational infrastructure. | Prompt traffic on the production API terminates inside the attested gateway. GCP services store metadata, billing records, secrets, and operational logs as configured. TrustedRouter never logs prompt/output content; ordinary synchronous and streaming inference does not retain it. The opt-in Batch API temporarily retains enclave-encrypted artifacts for up to 30 days. | Policy |
| Cloudflare | DNS, public-site caching, status/trust hosting support, and edge protection for non-prompt surfaces. | Public website traffic and DNS metadata. Production prompt TLS is designed to terminate inside the attested gateway, not inside the control-plane site. | Policy |
| Stripe | Card payments, stablecoin checkout, customer records, saved payment methods, invoices, and billing webhooks. | Billing identity and payment metadata. No prompt/output content. | Policy |
| PayPal | Optional PayPal payment processing for prepaid credits. | Billing identity and payment metadata. No prompt/output content. | Policy |
| Amazon Web Services SES/SNS | Transactional email delivery, bounce handling, complaint handling, and email-domain verification. | Email address and transactional email metadata. No prompt/output content. | Policy |
| Sentry | Control-plane exception monitoring. | Scrubbed control-plane errors and metadata. Sentry is not configured in the attested prompt gateway and must not receive prompts, outputs, API keys, or BYOK secrets. | Policy |
| Axiom | Operational log search and alerting. | Structured operational metadata. Prompt/output content must not be logged. | Policy |
| Exa | Optional hosted web search for Responses API requests that explicitly enable the web_search tool. | A model-generated search query, requested domain and country filters, and search metadata. Search runs only inside the attested gateway. Exa does not receive the original prompt or model output directly, but a generated query can reflect prompt content. Web search is blocked on ZDR, E2E/confidential, and EU privacy routes until a compatible contractual posture is approved. | Policy |
| GitHub | Source control, CI, release workflows, and public open-source repositories. | Source code, CI metadata, and release artifacts. No production prompt/output content. | Policy |
Model provider subprocessors
Downstream model compute providers.
Unknown means no tracked public or contracted claim is currently published in the TrustedRouter catalog.
| Provider | ZDR | Confidential compute | Provider E2EE | Purpose | Policy source |
|---|---|---|---|---|---|
| Tinfoiltinfoil | yes | yes | yes | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Tracked as a confidential inference provider with attested provider compute and no prompt/output logging claims. |
Policy source |
| NEAR AInear-ai | unknown | yes | yes | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. TrustedRouter connects directly to the model workload and verifies the live TLS key, Intel TDX quote, NVIDIA GPUs, deployment action log, and pinned workload inside the TrustedRouter enclave before sending content. Verification fails closed. No separate ZDR claim is currently tracked. |
Policy source |
| Chuteschutes | yes | yes | yes | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. TrustedRouter encrypts each request to an attested Chutes workload and verifies Intel TDX plus NVIDIA GPU attestation inside the TrustedRouter enclave before sending content. Verification fails closed. Chutes also documents no prompt/output storage or training. |
Policy source |
| Basetenbaseten | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| Cerebrascerebras | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Tracked as provider-ZDR. Cerebras documents zero-retention inference and ZDR-compliant ephemeral prompt caching that is never persisted. |
Policy source |
| Coherecohere | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Marked ZDR — Cohere does not retain prompt/response content for TrustedRouter's configured account and does not train on customer API data. (Not a confidential-compute/TEE provider.) |
Policy source |
| Engyengy | yes | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Engy states that prompts, outputs, tool arguments, images, and embeddings are not stored or used for training. It retains request metadata such as model, token counts, cost, and latency. Engy's verified-inference sampling is not a user-verifiable TEE attestation, so this route is ZDR but not confidential or E2EE. |
Policy source |
| Google Vertex AIgoogle-vertex | prepaid only | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. TrustedRouter's managed Vertex AI account is covered by contractual Zero Data Retention. This guarantee applies only to TrustedRouter-funded routes. TrustedRouter does not invoke Google Search or Maps grounding or Gemini Live session resumption on these routes. Google AI Studio is classified separately. |
Policy source |
| Inceptroninceptron | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Inceptron documents zero retention by default: API prompts and outputs are processed transiently and discarded after processing. |
Policy source |
| Nebius Token Factorynebius | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| OpenAIopenai | prepaid only | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Contracted Zero Data Retention is active for TrustedRouter's managed OpenAI account, effective July 28, 2026, and live enforcement was verified on July 29, 2026. This guarantee applies only to TrustedRouter-funded routes; customer BYOK credentials use the data controls on the customer's own OpenAI organization or project. |
Policy source |
| Parasailparasail | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| Phalaphala | yes | yes | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Phala publishes TDX/GPU attestation and signed request receipts, but TrustedRouter does not yet verify the complete receipt chain on every routed request. The route is therefore not classified as provider E2EE and is excluded from trustedrouter/e2e. |
Policy source |
| Togethertogether | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| Voyage AIvoyage | yes | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Marked ZDR — Voyage AI does not retain prompt content for TrustedRouter's configured account and does not train on customer API data. (Not a confidential-compute/TEE provider.) |
Policy source |
| 0G Private Computerzero-g | unknown | yes | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 0G labels these routes private, TeeML, TEE-attested, and healthy. TrustedRouter requests that mode with X-0G-Provider-Trust-Mode: private and excludes standard and TeeTLS routes. The current live 0G router path does not expose the route quote, audited code measurement, or response authentication needed for TrustedRouter to verify and encrypt each request end to end, so 0G is not in the trustedrouter/e2e pool. |
Policy source |
| Aion Labsaion-labs | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Aion Labs account. This route is Standard. |
Policy source |
| AkashMLakashml | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's AkashML account. This route is Standard. |
Policy source |
| Alibaba Cloud Model Studioalibaba | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Alibaba Cloud Model Studio model availability and pricing are linked for users who need to review API data handling and regional deployment scope. |
Policy source |
| Anthropicanthropic | no | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Not currently marked ZDR in TrustedRouter. Anthropic may offer contracted or account-specific data-retention terms, but this provider is excluded from trustedrouter/zdr until that posture is reverified. |
Policy source |
| Arcee AIarcee | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Arcee account. This route is Standard. |
Policy source |
| Atlas Cloudatlas-cloud | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| Baidu AI Cloud Qianfanbaidu | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Credentials are staged for provider discovery, but no canaried route with exact first-party pricing is published yet. No contractual ZDR, confidential-compute, or E2EE claim is tracked. |
Policy source |
| Black Forest Labsbfl | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Black Forest Labs does not publish contractual zero retention, confidential compute, or end-to-end encryption for the hosted FLUX API. This route is Standard. |
Policy source |
| BytePlus ModelArkbyteplus | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. The BytePlus ModelArk key authenticates and discovers direct model IDs, but this account has not activated the model service. Routes remain dark until activation, a paid canary, and exact first-party pricing all succeed. |
Policy source |
| Cloudflare Workers AIcloudflare-workers-ai | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Cloudflare's Workers AI documentation is linked for model and data-handling review. |
Policy source |
| Crusoecrusoe | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| Darkbloomdarkbloom | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Credentials are staged for provider discovery, but no canaried route with exact first-party pricing is published yet. No contractual ZDR, confidential-compute, or E2EE claim is tracked. |
Policy source |
| Databricksdatabricks | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Databricks Foundation Model APIs are a Designated Service and pay-per-token workloads are HIPAA compliant. Databricks may temporarily process or store inputs and outputs for abuse prevention, and may process data outside the originating cloud or region. This route is therefore standard privacy, not ZDR, confidential compute, or end-to-end encrypted. |
Policy source |
| Decartdecart | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Decart's public terms permit service-related use of submitted content and do not promise zero retention or confidential compute. This route is Standard. |
Policy source |
| DeepInfradeepinfra | no | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| DeepSeekdeepseek | no | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Not ZDR. DeepSeek's published privacy policy says prompts/inputs may be collected and personal data may be used to train or improve machine learning models and algorithms. |
Policy source |
| DigitalOcean Gradient AIdigitalocean | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. DigitalOcean's Gradient AI model and pricing documentation is linked for data-handling review. |
Policy source |
| fal.aifal | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. TrustedRouter supports bounded fal image generation and MiniMax H3 Max video generation with first-party pricing and paid generation canaries. H3 Max video is returned inline through fal's fixed queue host rather than a provider-selected download host. No contractual ZDR, confidential-compute, or E2EE claim is tracked. |
Policy source |
| Featherless AIfeatherless | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Featherless routes are limited to chat models explicitly available on TrustedRouter's current plan with exact prices in Featherless's authenticated catalog. No contractual ZDR, confidential-compute, or E2EE claim is tracked for this account, so these routes are Standard. |
Policy source |
| Fireworks AIfireworks | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| FriendliAIfriendli | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Friendli's legal/privacy terms are linked for users who need to review API data handling. |
Policy source |
| GMI Cloudgmi | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. GMI runs isolated/VPC GPU inference, but that is network isolation, NOT an attested TEE — so no confidential-compute, zero-retention, or E2EE claim is marked. Retention/training terms are unverified (the published policy page is JavaScript-only and would not render). |
Policy source |
| Google AI Studiogoogle-ai-studio | no | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Not currently marked ZDR in TrustedRouter. Google AI Studio and the Gemini Developer API have product- and billing-specific data-use terms, so this route stays outside trustedrouter/zdr. |
Policy source |
| Hugging Face Inference Providershuggingface | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Credentials are staged for provider discovery, but no canaried route with an unambiguous downstream provider and exact price is published. No contractual ZDR, confidential-compute, or E2EE claim is tracked. |
Policy source |
| Inception Labsinception | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Inception account. This route is Standard. |
Policy source |
| IO Intelligenceio-net | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. IO Intelligence publishes exact per-token prices in its authenticated catalog. TrustedRouter admits only priced routes that pass a live chat canary. No contractual ZDR, confidential-compute, or E2EE claim is tracked for this account, so these routes are Standard. |
Policy source |
| Jina AIjina | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Jina routes are embedding-only and use exact prices from Jina's authenticated model catalog. No contractual ZDR, confidential-compute, or E2EE claim is tracked for this account, so these routes are Standard. |
Policy source |
| Kimikimi | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Kimi/Moonshot policy source is linked for users who need to review API retention and processing terms. |
Policy source |
| Kling AIkling | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR, confidential-compute, or E2EE claim is tracked for the Kling video API. TrustedRouter relays and does not durably store prompt or generated video content. |
Policy source |
| Kreakrea | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Krea exposes an asynchronous media API, not a shared OpenAI-compatible chat catalog. TrustedRouter supports Krea 2 Medium with exact fixed per-image billing. The route remains dark until its paid generation canary succeeds. No ZDR or confidential-compute claim is tracked. |
Policy source |
| Lightning AIlightning | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Lightning's general privacy and security documentation is linked for retention review. |
Policy source |
| Lightricks LTXltx | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR, confidential-compute, or E2EE claim is tracked for the LTX video API. TrustedRouter relays and does not durably store prompt or generated video content. |
Policy source |
| Liquid AIliquid | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Liquid's configured developer credentials target model deployment and bundling rather than a shared token-priced inference API. The provider remains non-routable until a concrete hosted endpoint is configured. |
Policy source |
| Makoramakora | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Makora's inference and privacy documentation are linked for users who need to review API data handling. |
Policy source |
| Mancermancer | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Mancer account. This route is Standard. |
Policy source |
| Meta via OpenRoutermeta | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. TrustedRouter sends requests through its attested gateway to OpenRouter, which routes them to Meta. This downstream route is not marked zero-retention, confidential-compute, or end-to-end encrypted. |
Policy source |
| Microsoft Azure AI Foundryazure | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR, confidential-compute, or E2EE claim is currently tracked for TrustedRouter's Microsoft Foundry account. Azure model availability and pricing are synchronized directly from the account. |
Policy source |
| MiniMaxminimax | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. MiniMax's product privacy overview is linked for users who need to review API/open-platform terms. |
Policy source |
| Mistralmistral | no | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. TrustedRouter's managed Mistral account has model-training use disabled, so new input and output sent through TR-funded routes is opted out of model training. This is not zero data retention: Mistral's published policy says ordinary API input and output may be retained for 30 rolling days unless ZDR is separately activated. Customer BYOK accounts keep their own Mistral privacy settings. |
Policy source |
| Modalmodal | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. The configured Modal credentials deploy workloads; they do not identify a shared model catalog. Modal remains non-routable until explicit deployment endpoints and prices are configured. |
Policy source |
| Morphmorph | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Morph's public paid tier documents up to 30 days of content retention. Zero retention is reserved for enterprise contracts. |
Policy source |
| Neurometric AIneurometric | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Neurometric states that TrustedRouter requests run with upstream trace logging disabled: prompts and completions are not written to observability or object storage, and only aggregate request counts and token totals are retained. This is classified as no-store, not contractual ZDR or confidential compute. |
Policy source |
| NextBitnextbit | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's NextBit account. This route is Standard. |
Policy source |
| Novita AInovita | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| Nscalenscale | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Nscale publishes a general nonlogging statement for serverless inference, but TrustedRouter has not verified a contractual zero-retention commitment for this account. These routes remain Standard and make no confidential-compute or E2EE claim. |
Policy source |
| NVIDIA NIMnvidia-nim | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. NVIDIA's hosted NIM API Catalog endpoints are preview services for development and prototyping. TrustedRouter exposes chat-capable models from its configured API Catalog key as Standard routes. NVIDIA requires an NVIDIA AI Enterprise entitlement for production deployments. NVIDIA does not publish hosted preview token rates, so TrustedRouter uses a conservative fallback price and excludes these routes from price indexing. |
Policy source |
| OpenRouteropenrouter | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. TrustedRouter sends requests through its attested gateway to OpenRouter, which routes them to a downstream operator. Routes here are Standard privacy and are excluded from ZDR, confidential-compute, and E2EE routing. |
Policy source |
| OVHcloudovhcloud | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Not routable: the configured OVH credential is not an AI Endpoints access token and the live model catalog rejects it. The provider stays listed while a valid inference token is obtained. |
Policy source |
| Pearl Research Labspearl | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| Perceptronperceptron | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Perceptron account. Its public catalog is priced, but the configured inference credential did not authenticate during the live canary, so routes remain dark. |
Policy source |
| Perplexityperplexity | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Perplexity account. Sonar runs with low search context and its first-party token and fixed successful-request charges settle exactly. This route is Standard. |
Policy source |
| Poolsidepoolside | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Credentials are staged, but no shared canaried catalog with exact first-party token pricing is published yet. No contractual ZDR, confidential-compute, or E2EE claim is tracked. |
Policy source |
| Recraftrecraft | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Recraft's developer terms say API inputs and outputs are not used to train its models, but do not promise zero retention or confidential compute. This route is Standard. |
Policy source |
| Reka AIreka | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Reka account. This route is Standard. |
Policy source |
| Relacerelace | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Relace's public API documentation does not publish contractual zero retention, confidential compute, or end-to-end encryption for hosted open-model requests. This route is Standard. |
Policy source |
| Riverflowriverflow | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Riverflow is a variable-credit media workflow API, not a shared token-priced chat endpoint. Its configured credential is rejected by the live MCP endpoint, and no exact per-job billable receipt is exposed. It remains fail-closed until both contracts are available. |
Policy source |
| Runwayrunway | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR, confidential-compute, or E2EE claim is tracked for the Runway video API. TrustedRouter relays and does not durably store prompt or generated video content. |
Policy source |
| Sail Researchsail-research | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Sail Research account. This route is Standard. |
Policy source |
| Sakana AIsakana | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Sakana account. Version-pinned routes use Sakana's first-party token prices and authenticated availability. |
Policy source |
| SambaNovasambanova | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's SambaNova account. This route is Standard. |
Policy source |
| Scalewayscaleway | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Scaleway routes are discovered from its authenticated Model as a Service catalog and priced from Scaleway's first-party EUR price feed with a bounded FX reserve. No contractual ZDR, confidential-compute, or E2EE claim is tracked for this account, so these routes are Standard. |
Policy source |
| SiliconFlowsiliconflow | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. SiliconFlow's privacy policy source is linked for retention and interaction-data terms. |
Policy source |
| StepFunstepfun | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. StepFun's public privacy policy does not provide contractual zero retention or confidential-compute guarantees for API requests. TrustedRouter therefore classifies this route as Standard. |
Policy source |
| StreamLakestreamlake | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked. StreamLake's public privacy policy is linked for API data-handling review. |
Policy source |
| Telnyxtelnyx | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR or confidential-compute claim is tracked here. Telnyx's privacy policy is linked for users who need to review inference data handling. |
Policy source |
| Tencent Cloud TokenHubtencent | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. The TokenHub inference key authenticates and its provider-native catalog is discoverable, but inference is blocked by insufficient account balance. Routes remain dark until a paid canary succeeds and exact first-party postpaid prices are joined. |
Policy source |
| Thinking Machines Labthinkingmachines | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Thinking Machines Lab's model and pricing documentation is linked for model capability and API review. |
Policy source |
| Upstageupstage | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Upstage account. This route is Standard. |
Policy source |
| Venicevenice | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Mixed model-specific posture. TrustedRouter cannot independently verify a complete chain from a live Venice endpoint through immutable source and hardware measurements to committed model weights. Venice is therefore not tracked as confidential or E2EE. Exact routes marked Private in Venice's live catalog qualify only as policy-backed ZDR through endpoint-specific records; Anonymized routes do not. |
Policy source |
| Vultrvultr | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Not routable: the configured credential is rejected by both Vultr's account API and Serverless Inference API. Vultr issues a distinct inference key per subscription; the provider stays listed until that key is available. |
Policy source |
| Waferwafer | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. Wafer supports request-scoped ZDR via Wafer-ZDR: required on supported models; model-level support differs, so TrustedRouter keeps provider-level claims conservative. |
Policy source |
| Weights & Biaseswandb | no | no | no | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
| xAI Grokgrok | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. xAI documents no training on API requests and 30-day default audit retention, with ZDR as an enterprise feature. |
Policy source |
| Xiaomi MiMoxiaomi | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. No provider-ZDR claim is tracked here. Xiaomi MiMo's open-platform terms are linked for users who need to review API data handling. |
Policy source |
| Z.AIzai | unknown | unknown | unknown | For ordinary inference, prompt/output content is processed in transit for requests routed to this provider. Opt-in provider-native Batch may temporarily retain plaintext input for up to 26 hours and provider results for up to 6 hours after availability; request metadata needed for billing, routing, abuse controls, and support may also be processed. 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. |
Policy source |
