P
Phala
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-07-212026-08-19
Inference Latency
OpenAI: gpt-oss-20b558ms TTFT · 50 TPS
Qwen: Qwen2.5 7B Instruct291ms TTFT · 52 TPS
Google: Gemma 4 31B3234ms TTFT · 23 TPS
Google: Gemma 3 27B1985ms TTFT · 17 TPS
OpenAI: gpt-oss-120b884ms TTFT · 69 TPS
DeepSeek: DeepSeek V4 Flash 07312363ms TTFT · 51 TPS
Qwen: Qwen3.6 35B A3B1570ms TTFT · 19 TPS
DeepSeek: DeepSeek V4 Flash 04233629ms TTFT · 9 TPS
Meta: Muse Glimmer 30B1397ms TTFT · 43 TPS
Qwen: Qwen3.5-27B1541ms TTFT · 29 TPS
Qwen: Qwen3.6 27B925ms TTFT · 33 TPS
Qwen: Qwen3.5 397B A17B1795ms TTFT · 33 TPS
MoonshotAI: Kimi K2.51987ms TTFT · 28 TPS
DeepSeek: DeepSeek V3.23501ms TTFT · 9 TPS
MoonshotAI: Kimi K2.61624ms TTFT · 17 TPS
Z.ai: GLM 5.11968ms TTFT · 36 TPS
Z.ai: GLM 5.22040ms TTFT · 30 TPS
MoonshotAI: Kimi K33067ms TTFT · 37 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| OpenAI: gpt-oss-20b | $0.04 | $0.15 | 558ms | 50 |
| Qwen: Qwen2.5 7B Instruct | $0.10 | $0.20 | 291ms | 52 |
| Google: Gemma 4 31B | $0.15 | $0.46 | 3234ms | 23 |
| Google: Gemma 3 27B | $0.15 | $0.46 | 1985ms | 17 |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 884ms | 69 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.20 | $0.40 | 2363ms | 51 |
| Qwen: Qwen3.6 35B A3B | $0.20 | $1.27 | 1570ms | 19 |
| DeepSeek: DeepSeek V4 Flash 0423 | $0.20 | $0.40 | 3629ms | 9 |
| Meta: Muse Glimmer 30B | $0.30 | $1.10 | 1397ms | 43 |
| Qwen: Qwen3.5-27B | $0.30 | $2.40 | 1541ms | 29 |
| Qwen: Qwen3.6 27B | $0.32 | $2.70 | 925ms | 33 |
| Qwen: Qwen3.5 397B A17B | $0.55 | $3.50 | 1795ms | 33 |
| MoonshotAI: Kimi K2.5 | $0.60 | $3.00 | 1987ms | 28 |
| DeepSeek: DeepSeek V3.2 | $1.00 | $1.00 | 3501ms | 9 |
| MoonshotAI: Kimi K2.6 | $1.09 | $4.60 | 1624ms | 17 |
| Z.ai: GLM 5.1 | $1.21 | $4.20 | 1968ms | 36 |
| Z.ai: GLM 5.2 | $1.26 | $3.00 | 2040ms | 30 |
| MoonshotAI: Kimi K3 | $3.00 | $15.00 | 3067ms | 37 |
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.