W
Wafer
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-09-192026-10-18
Inference Latency
Z.ai: GLM 5.2472ms TTFT · 135 TPS
Qwen: Qwen3.8 27B546ms TTFT · 95 TPS
Z.ai: GLM 5.3527ms TTFT · 125 TPS
DeepSeek: DeepSeek V4.1 Flash531ms TTFT · 69 TPS
Z.ai: GLM 5.3 Flash403ms TTFT · 154 TPS
DeepSeek: DeepSeek V4 Flash 0731433ms TTFT · 169 TPS
Z.ai: GLM 5.3438ms TTFT · 124 TPS
Z.ai: GLM 5.2592ms TTFT · 139 TPS
DeepSeek: DeepSeek V4 Pro 0813476ms TTFT · 126 TPS
MoonshotAI: Kimi K3787ms TTFT · 60 TPS
MoonshotAI: Kimi K3843ms TTFT · 58 TPS
DeepSeek: DeepSeek V4.1 Flash 10172264ms TTFT · 78 TPS
DeepSeek: DeepSeek V4 Flash 0423803ms TTFT · 67 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Z.ai: GLM 5.2 | $0.03 | $7.00 | 472ms | 135 |
| Qwen: Qwen3.8 27B | $0.04 | $2.30 | 546ms | 95 |
| Z.ai: GLM 5.3 | $0.08 | $2.50 | 527ms | 125 |
| DeepSeek: DeepSeek V4.1 Flash | $0.10 | $0.65 | 531ms | 69 |
| Z.ai: GLM 5.3 Flash | $0.12 | $0.50 | 403ms | 154 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.13 | $0.23 | 433ms | 169 |
| Z.ai: GLM 5.3 | $0.18 | $2.50 | 438ms | 124 |
| Z.ai: GLM 5.2 | $0.19 | $10.00 | 592ms | 139 |
| DeepSeek: DeepSeek V4 Pro 0813 | $0.25 | $5.00 | 476ms | 126 |
| MoonshotAI: Kimi K3 | $0.28 | $16.00 | 787ms | 60 |
| MoonshotAI: Kimi K3 | $0.36 | $11.90 | 843ms | 58 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.40 | $1.60 | 2264ms | 78 |
| DeepSeek: DeepSeek V4 Flash 0423 | $0.70 | $0.17 | 803ms | 67 |
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.