P
Phala
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-03-232026-04-21
Inference Latency
Qwen: Qwen2.5 7B Instruct922ms TTFT · 26 TPS
OpenAI: gpt-oss-120b1231ms TTFT · 24 TPS
Z.ai: GLM 4.7 Flash1382ms TTFT · 23 TPS
Google: Gemma 3 27B720ms TTFT · 27 TPS
Qwen: Qwen3 VL 30B A3B Instruct1127ms TTFT · 20 TPS
Qwen: Qwen3.5-27B677ms TTFT · 11 TPS
MoonshotAI: Kimi K2.52625ms TTFT · 17 TPS
Z.ai: GLM 51964ms TTFT · 23 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Qwen: Qwen2.5 7B Instruct | $0.04 | $0.10 | 922ms | 26 |
| OpenAI: gpt-oss-120b | $0.10 | $0.49 | 1231ms | 24 |
| Z.ai: GLM 4.7 Flash | $0.10 | $0.43 | 1382ms | 23 |
| Google: Gemma 3 27B | $0.11 | $0.40 | 720ms | 27 |
| Qwen: Qwen3 VL 30B A3B Instruct | $0.20 | $0.70 | 1127ms | 20 |
| Qwen: Qwen3.5-27B | $0.30 | $2.40 | 677ms | 11 |
| MoonshotAI: Kimi K2.5 | $0.60 | $3.00 | 2625ms | 17 |
| Z.ai: GLM 5 | $1.20 | $3.50 | 1964ms | 23 |
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.