GMI Cloud
Try GMI Cloud on us. Starter credit covers your first requests, then one key reaches all 6 GMI Cloud models, with the privacy posture shown on every route.
GMI Cloudgmi
These privacy labels describe GMI Cloud, 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 | GMI Cloud |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://www.gmicloud.ai/ |
| Models | 6 public models |
| Credits routes | 6 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | 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 |
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
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet 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.
Measured performance
15 samplesContinuously sampled across GMI Cloud's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 2537 ms |
|---|---|
| Effective throughput | 53 tok/s n=3 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5.1 | 1831 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v4-pro | 1844 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 2537 ms | 47 tok/s n=1 | 100.00% | — | 4 |
| z-ai/glm-5.2 | 2628 ms | 53 tok/s n=2 | 100.00% | — | 1 |
| z-ai/glm-5 | 3203 ms | — | 100.00% | — | 2 |
| tencent/hy4-preview | 3311 ms | — | 100.00% | — | 2 |
| inclusionai/ling-3.0-flash-fin | — | — | — | 1 provider_error |
0 |
| moonshotai/kimi-k2-thinking | — | — | — | 1 provider_error |
0 |
GMI Cloud performance history · Full provider & model leaderboard.
Models served by GMI Cloud.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 |
IQ 123#31 | 1,048,576 | $1.8357/1M | $0.152975/1M | $3.6714/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#21 | 1,048,576 | $3.165/1M | $0.3165/1M | $15.825/1M |
tencent/hy4-previewTencent: Hy4 preview |
IQ 113#63 | 1,000,000 | $0.87987/1M | $0.04431/1M | $2.638555/1M |
z-ai/glm-5Z.ai: GLM 5 |
IQ 107#87 | 202,752 | $1.055/1M | $0.211/1M | $3.376/1M |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 113#62 | 202,752 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 118#48 | 1,048,576 | $1.477/1M | $0.2743/1M | $4.642/1M |
Questions
Does GMI Cloud have zero data retention?
TrustedRouter does not currently mark GMI Cloud as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is GMI Cloud end-to-end encrypted?
TrustedRouter does not currently mark GMI Cloud 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 GMI Cloud models are available through TrustedRouter?
This page currently lists 6 public GMI Cloud models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.