D
DekaLLM
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-05-222026-06-20
Inference Latency
Mistral: Mistral Nemo767ms TTFT · 16 TPS
OpenAI: gpt-oss-20b1299ms TTFT · 34 TPS
OpenAI: gpt-oss-120b770ms TTFT · 8 TPS
Google: Gemma 4 26B A4B 2623ms TTFT · 10 TPS
NVIDIA: Nemotron 3 Super5421ms TTFT · 5 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Mistral: Mistral Nemo | $0.02 | $0.03 | 767ms | 16 |
| OpenAI: gpt-oss-20b | $0.03 | $0.14 | 1299ms | 34 |
| OpenAI: gpt-oss-120b | $0.04 | $0.18 | 770ms | 8 |
| Google: Gemma 4 26B A4B | $0.06 | $0.33 | 2623ms | 10 |
| NVIDIA: Nemotron 3 Super | $0.09 | $0.45 | 5421ms | 5 |
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.