C
Crusoe
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-07-212026-08-19
Inference Latency
NVIDIA: Nemotron 3 Nano 30B A3B247ms TTFT · 131 TPS
Google: Gemma 4 31B733ms TTFT · 30 TPS
Meta: Llama 3.3 70B Instruct380ms TTFT · 54 TPS
DeepSeek: DeepSeek V3 0324424ms TTFT · 16 TPS
MoonshotAI: Kimi K2.6536ms TTFT · 44 TPS
Z.ai: GLM 5.1846ms TTFT · 57 TPS
Z.ai: GLM 5.2846ms TTFT · 48 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| NVIDIA: Nemotron 3 Nano 30B A3B | $0.05 | $0.20 | 247ms | 131 |
| Google: Gemma 4 31B | $0.14 | $0.40 | 733ms | 30 |
| Meta: Llama 3.3 70B Instruct | $0.25 | $0.75 | 380ms | 54 |
| DeepSeek: DeepSeek V3 0324 | $0.50 | $1.50 | 424ms | 16 |
| MoonshotAI: Kimi K2.6 | $0.70 | $3.50 | 536ms | 44 |
| Z.ai: GLM 5.1 | $1.20 | $4.40 | 846ms | 57 |
| Z.ai: GLM 5.2 | $1.40 | $4.40 | 846ms | 48 |
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.