D
DekaLLM
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-03-232026-04-21
Inference Latency
NVIDIA: Nemotron 3 Super939ms TTFT · 1 TPS
Z.ai: GLM 4.71382ms TTFT · 22 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| NVIDIA: Nemotron 3 Super | $0.09 | $0.45 | 939ms | 1 |
| Z.ai: GLM 4.7 | $0.38 | $1.74 | 1382ms | 22 |
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.