GMI Cloud
Explore GMI Cloud models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
GMI Cloudgmi
No provider claim
These privacy labels describe GMI Cloud, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | GMI Cloud |
|---|---|
| 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 |
Measured performance
34 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 | 3924 ms |
|---|---|
| Effective throughput | 23 tok/s n=1 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5 | 1825 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.1 | 2672 ms | — | 100.00% | — | 5 |
| z-ai/glm-5.2 | 3086 ms | — | 100.00% | — | 7 |
| tencent/hy4-preview | 3924 ms | — | 100.00% | — | 7 |
| deepseek/deepseek-v4-pro | 4026 ms | — | 100.00% | — | 5 |
| moonshotai/kimi-k3 | 5523 ms | 23 tok/s n=1 | 100.00% | — | 8 |
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 114#47 | 1,048,576 | $1.8357/1M | $0.152975/1M | $3.6714/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 121#27 | 1,048,576 | $3.165/1M | $0.3165/1M | $15.825/1M |
tencent/hy4-previewtencent/hy4-preview |
IQ # | 262,144 | $0.87987/1M | $0.04431/1M | $2.638555/1M |
z-ai/glm-5Z.ai: GLM 5 |
IQ 105#75 | 202,752 | $1.055/1M | $0.211/1M | $3.376/1M |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 113#49 | 202,752 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#28 | 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.