N
NextBit
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-09-192026-10-18
Inference Latency
Google: Gemma 3 12B590ms TTFT · 48 TPS
Google: Gemma 4 26B A4B 589ms TTFT · 37 TPS
Google: Gemma 3 27B654ms TTFT · 43 TPS
NeverSleep: Lumimaid v0.2 8B366ms TTFT · 95 TPS
Qwen: Qwen3 14B335ms TTFT · 53 TPS
Z.ai: GLM 5.3 Flash630ms TTFT · 122 TPS
DeepSeek: R1 Distill Qwen 32B753ms TTFT · 23 TPS
ReMM SLERP 13B847ms TTFT · 22 TPS
Google: Gemma 2 27B1352ms TTFT · 56 TPS
Sao10K: Llama 3.3 Euryale 70B1136ms TTFT · 18 TPS
Noromaid 20B773ms TTFT · 31 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Google: Gemma 3 12B | $0.05 | $0.15 | 590ms | 48 |
| Google: Gemma 4 26B A4B | $0.07 | $0.22 | 589ms | 37 |
| Google: Gemma 3 27B | $0.08 | $0.35 | 654ms | 43 |
| NeverSleep: Lumimaid v0.2 8B | $0.09 | $0.60 | 366ms | 95 |
| Qwen: Qwen3 14B | $0.10 | $0.22 | 335ms | 53 |
| Z.ai: GLM 5.3 Flash | $0.25 | $0.70 | 630ms | 122 |
| DeepSeek: R1 Distill Qwen 32B | $0.29 | $0.29 | 753ms | 23 |
| ReMM SLERP 13B | $0.45 | $0.65 | 847ms | 22 |
| Google: Gemma 2 27B | $0.65 | $0.65 | 1352ms | 56 |
| Sao10K: Llama 3.3 Euryale 70B | $0.65 | $0.75 | 1136ms | 18 |
| Noromaid 20B | $1.00 | $1.75 | 773ms | 31 |
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.