Skip to content
llmwaves

Inference provider

Phala

19 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.

Models served

19

Median output speed

127 t/s

Median latency

409ms

Median price / 1M

$0.845

Catalogue

Strongest and fastest on this provider

What the catalogue looks like at the top end, on the two axes that usually decide the choice.

Highest Intelligence Index

Among models this provider serves

View as table
ModelIntelligence
GLM 5.3 (Z.ai)44.8
Kimi K3 (Moonshot AI)43.6
GLM 5.3 Flash (Z.ai)41.8
V4.1 Flash (DeepSeek)39.5
V4 Pro 0813 (DeepSeek)36.0
V4 Flash 0731 (DeepSeek)34.3
Qwen3.8 27B (Qwen)33.7
GLM 5.2 (Z.ai)33.7
Kimi K2.6 (Moonshot AI)27.0
GLM 5.1 (Z.ai)26.1

Fastest output

Median tokens per second

View as table
ModelTokens/s
gpt-oss-120b (OpenAI)641
Qwen3.8 27B (Qwen)409
GLM 5.2 (Z.ai)368
V4.1 Flash (DeepSeek)296
V4 Flash 0731 (DeepSeek)223
Kimi K2.6 (Moonshot AI)146
GLM 5.3 Flash (Z.ai)141
GLM 5.3 (Z.ai)138
Qwen3.6 35B A3B (Qwen)128
Kimi K2.7 Code (Moonshot AI)127

Full catalogue

All 19 models on Phala

Filter by creator
19 of 19 models
GLM 5.3
Z.aiopen
44.8$0.39
Kimi K3
Moonshot AIopen
43.6$1.22
GLM 5.3 Flash
Z.aiopen
41.8$0.05
V4.1 Flash
DeepSeekopen
39.5$0.07
V4 Pro 0813
DeepSeekopen
36.0$0.38
V4 Flash 0731
DeepSeekopen
34.3$0.05
Qwen3.8 27B
Qwenopen
33.7$0.19
GLM 5.2
Z.aiopen
33.7$0.56
Kimi K2.6
Moonshot AIopen
27.0$0.31
GLM 5.1
Z.aiopen
26.1$0.29
Kimi K2.7 Code
Moonshot AIopen
25.8$0.30
Hy3
Tencentopen
25.3$0.05
Qwen3.5-27B
Qwenopen
22.9$0.22
Qwen3.6 27B
Qwenopen
21.4$0.27
Qwen3.5 397B A17B
Qwenopen
18.4$0.31
Qwen3.6 35B A3B
Qwenopen
18.2$0.09
V3.2
DeepSeekopen
16.0$0.08
gpt-oss-120b
OpenAIopen
11.6$0.06
Qwen2.5 7B Instruct
Qwenopen
—$0.01