G
GMICloud
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-05-222026-06-20
Inference Latency
Tencent: Hy3 preview8781ms TTFT · 30 TPS
DeepSeek: DeepSeek V4 Flash2577ms TTFT · 28 TPS
DeepSeek: DeepSeek V3 03242471ms TTFT · 21 TPS
Qwen: Qwen3.5 397B A17B2641ms TTFT · 38 TPS
Z.ai: GLM 57290ms TTFT · 31 TPS
Z.ai: GLM 5.13657ms TTFT · 38 TPS
DeepSeek: DeepSeek V4 Pro948ms TTFT · 50 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Tencent: Hy3 preview | $0.06 | $0.21 | 8781ms | 30 |
| DeepSeek: DeepSeek V4 Flash | $0.10 | $0.20 | 2577ms | 28 |
| DeepSeek: DeepSeek V3 0324 | $0.29 | $1.14 | 2471ms | 21 |
| Qwen: Qwen3.5 397B A17B | $0.60 | $3.60 | 2641ms | 38 |
| Z.ai: GLM 5 | $0.60 | $1.92 | 7290ms | 31 |
| Z.ai: GLM 5.1 | $0.98 | $3.08 | 3657ms | 38 |
| DeepSeek: DeepSeek V4 Pro | $1.13 | $2.26 | 948ms | 50 |
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.