Fortanix
Try Fortanix on us. Starter credit covers your first requests, then one key reaches the Fortanix model, with its privacy posture shown on the route.
Fortanixfortanix
GLM 5.3 Flash with managed-route ZDR and operator-declared Santa Clara inference.
These privacy labels describe Fortanix, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Fortanix |
|---|---|
| API operator country | Not verified Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://www.fortanix.com/ |
| Models | 1 public model |
| Credits routes | 1 |
| Zero data retention | yes Reviewed TR-funded routes only; check each model |
| Verified confidential inference | Not verified |
| Policy note | Zero data retention for TrustedRouter's managed GLM-5.3-Flash route, confirmed by the operator on November 10, 2026. This account-scoped declaration does not establish provider-wide retention terms, confidential compute, or provider-side end-to-end encryption. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Santa Clara, California, United States
TrustedRouter's managed GLM-5.3-Flash route only. - Can locations change?
- Santa Clara datacenter, operator-confirmed; failover locations have not been verified.
- Provider region pinning
- No verified per-request geographic selector or attested residency receipt.
- Pinning through TrustedRouter
- Select provider.only=[fortanix] with allow_fallbacks=false; this does not pin TrustedRouter gateway geography.
- Infrastructure declaration
- Santa Clara inference by operator declaration, not hardware-attested residency.
- Evidence
- Direct operator confirmation on November 10, 2026; not inferred from headquarters or API ingress.. Reviewed .
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Models served by Fortanix.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
fortanix/glm-5.3-flashGLM 5.3 Flash (Fortanix) |
IQ 119#50 | 131,072 | $0.01/1M | Not published | $0.01/1M |
Questions
Does Fortanix have zero data retention?
Reviewed managed Fortanix routes can qualify for zero data retention. Check the exact model's endpoint policy: safety-retention, durable-cache and unreviewed routes are excluded. BYOK does not inherit this classification. Use provider.min_privacy=zdr to enforce eligibility.
Is Fortanix end-to-end encrypted?
TrustedRouter does not currently mark Fortanix as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Fortanix models are available through TrustedRouter?
This page currently lists 1 public Fortanix model, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.