G
GMICloud
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-07-212026-08-19
Inference Latency
DeepSeek: DeepSeek V4 Flash 04232631ms TTFT · 41 TPS
DeepSeek: DeepSeek V4 Flash 07312915ms TTFT · 47 TPS
Xiaomi: MiMo-V2.54442ms TTFT · 2 TPS
Tencent: Hy32203ms TTFT · 14 TPS
Tencent: Hy3 preview3095ms TTFT · 53 TPS
DeepSeek: DeepSeek V3.22167ms TTFT · 24 TPS
MiniMax: MiniMax M33362ms TTFT · 34 TPS
MiniMax: MiniMax M2.74167ms TTFT · 5 TPS
Xiaomi: MiMo-V2.5-Pro3864ms TTFT · 23 TPS
Z.ai: GLM 51526ms TTFT · 37 TPS
DeepSeek: DeepSeek V4 Pro 04233410ms TTFT · 33 TPS
Z.ai: GLM 5.22192ms TTFT · 30 TPS
Z.ai: GLM 5.12841ms TTFT · 60 TPS
DeepSeek: DeepSeek V4 Pro 08134083ms TTFT · 38 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| DeepSeek: DeepSeek V4 Flash 0423 | $0.08 | $0.17 | 2631ms | 41 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.11 | $0.22 | 2915ms | 47 |
| Xiaomi: MiMo-V2.5 | $0.12 | $0.24 | 4442ms | 2 |
| Tencent: Hy3 | $0.13 | $0.52 | 2203ms | 14 |
| Tencent: Hy3 preview | $0.18 | $0.60 | 3095ms | 53 |
| DeepSeek: DeepSeek V3.2 | $0.21 | $0.31 | 2167ms | 24 |
| MiniMax: MiniMax M3 | $0.24 | $0.96 | 3362ms | 34 |
| MiniMax: MiniMax M2.7 | $0.24 | $0.96 | 4167ms | 5 |
| Xiaomi: MiMo-V2.5-Pro | $0.30 | $0.61 | 3864ms | 23 |
| Qwen: Qwen3.5 397B A17B | $0.60 | $3.60 | — | — |
| Z.ai: GLM 5 | $0.60 | $1.92 | 1526ms | 37 |
| DeepSeek: DeepSeek V4 Pro 0423 | $0.70 | $1.39 | 3410ms | 33 |
| Z.ai: GLM 5.2 | $0.74 | $2.33 | 2192ms | 30 |
| Z.ai: GLM 5.1 | $0.91 | $2.86 | 2841ms | 60 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.19 | $3.56 | 4083ms | 38 |
Community Reviews
4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15
Reliable service, great API documentation.
mlresearcher
★★★★☆2025-06-10
Good performance but support could be faster.