OpenAI compatible API · Attested · Public status
GMI Cloud performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for GMI Cloud on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
GMI Cloudgmi
26 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 2647 ms |
|---|---|
| p95 TTFT | 5028 ms |
| Effective throughput | 104 tok/s n=3 |
| Uptime | 96.15% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| minimax/minimax-m3.1-flash | 2221 ms | — | 100.00% | — | 4 |
| z-ai/glm-5.2 | 2575 ms | 67 tok/s n=1 | 100.00% | — | 5 |
| deepseek/deepseek-v4-pro | 2647 ms | — | 100.00% | — | 4 |
| tencent/hy4-preview | 2670 ms | — | 75.00% | — | 4 |
| z-ai/glm-5.1 | 2802 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 3118 ms | 104 tok/s n=2 | 100.00% | — | 3 |
| z-ai/glm-5 | 3414 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-r1-0528 | — | — | — | 1 provider_error |
0 |
| inclusionai/ling-3.0-flash-fin | — | — | — | 1 provider_error |
0 |
| minimax/minimax-m2.5 | — | — | — | 3 provider_error |
0 |
| moonshotai/kimi-k2-thinking | — | — | — | 1 provider_error |
0 |