D
Darkbloom
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-09-192026-10-18
Inference Latency
OpenAI: gpt-oss-20b (free)3298ms TTFT · 22 TPS
OpenAI: gpt-oss-20b3513ms TTFT · 23 TPS
NVIDIA: Nemotron 3.5 Lightning1358ms TTFT · 30 TPS
Qwen: Qwen3.8 27B1336ms TTFT · 45 TPS
Google: Gemma 4 26B A4B 966ms TTFT · 48 TPS
Qwen: Qwen3.6 35B A3B1428ms TTFT · 41 TPS
Qwen: Qwen3.5-35B-A3B1258ms TTFT · 49 TPS
PrismML: Ternary Bonsai 2 27B5077ms TTFT · 32 TPS
Qwen: Qwen3.5-9B1545ms TTFT · 46 TPS
Xiaomi: MiMo-V2.6-Flash1954ms TTFT · 19 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| OpenAI: gpt-oss-20b (free) | $0.00 | $0.00 | 3298ms | 22 |
| OpenAI: gpt-oss-20b | $0.02 | $0.09 | 3513ms | 23 |
| NVIDIA: Nemotron 3.5 Lightning | $0.03 | $0.12 | 1358ms | 30 |
| Qwen: Qwen3.8 27B | $0.04 | $2.20 | 1336ms | 45 |
| Google: Gemma 4 26B A4B | $0.04 | $0.22 | 966ms | 48 |
| Qwen: Qwen3.6 35B A3B | $0.05 | $0.70 | 1428ms | 41 |
| Qwen: Qwen3.5-35B-A3B | $0.07 | $0.75 | 1258ms | 49 |
| PrismML: Ternary Bonsai 2 27B | $0.08 | $0.50 | 5077ms | 32 |
| Qwen: Qwen3.5-9B | $0.08 | $0.13 | 1545ms | 46 |
| Xiaomi: MiMo-V2.6-Flash | $0.10 | $0.28 | 1954ms | 19 |
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.