M
ModelRun
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
93.3%2026-09-192026-10-18
Inference Latency
DeepSeek: R1 0528 (free)154566ms TTFT · 4 TPS
Qwen: Qwen3.8 27B (free)381ms TTFT · 96 TPS
Qwen: Qwen3.8 27B439ms TTFT · 209 TPS
MiniMax: MiniMax M3586ms TTFT · 119 TPS
Google: Gemma 4 31B187ms TTFT · 200 TPS
Z.ai: GLM 5.3136ms TTFT · 204 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| DeepSeek: R1 0528 (free) | $0.00 | $0.00 | 154566ms | 4 |
| Qwen: Qwen3.8 27B (free) | $0.00 | $0.00 | 381ms | 96 |
| Qwen: Qwen3.8 27B | $0.20 | $2.50 | 439ms | 209 |
| MiniMax: MiniMax M3 | $0.30 | $1.30 | 586ms | 119 |
| Google: Gemma 4 31B | $0.75 | $1.00 | 187ms | 200 |
| Z.ai: GLM 5.3 | $2.10 | $6.60 | 136ms | 204 |
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.