D
DekaLLM
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-09-192026-10-18
Inference Latency
Mistral: Mistral Nemo820ms TTFT · 8 TPS
OpenAI: gpt-oss-20b798ms TTFT · 33 TPS
OpenAI: gpt-oss-120b494ms TTFT · 50 TPS
Qwen: Qwen3.8 27B986ms TTFT · 119 TPS
Google: Gemma 4 26B A4B 709ms TTFT · 52 TPS
NVIDIA: Nemotron 3 Super1854ms TTFT · 37 TPS
Qwen: Qwen3 30B A3B Instruct 2507405ms TTFT · 84 TPS
Qwen: Qwen3.6 35B A3B2686ms TTFT · 47 TPS
Z.ai: GLM 5.31729ms TTFT · 77 TPS
DeepSeek: DeepSeek V4 Pro 08132008ms TTFT · 92 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Mistral: Mistral Nemo | $0.02 | $0.03 | 820ms | 8 |
| OpenAI: gpt-oss-20b | $0.03 | $0.14 | 798ms | 33 |
| OpenAI: gpt-oss-120b | $0.03 | $0.18 | 494ms | 50 |
| Qwen: Qwen3.8 27B | $0.04 | $2.50 | 986ms | 119 |
| Google: Gemma 4 26B A4B | $0.06 | $0.33 | 709ms | 52 |
| NVIDIA: Nemotron 3 Super | $0.08 | $0.45 | 1854ms | 37 |
| Qwen: Qwen3 30B A3B Instruct 2507 | $0.09 | $0.30 | 405ms | 84 |
| Qwen: Qwen3.6 35B A3B | $0.10 | $1.00 | 2686ms | 47 |
| Z.ai: GLM 5.3 | $0.18 | $2.95 | 1729ms | 77 |
| DeepSeek: DeepSeek V4 Pro 0813 | $0.88 | $3.80 | 2008ms | 92 |
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.