The Known Good Updated 8 Sep 2026 Subscribe
Providers· Inference host· 28 tracked models

Phala — pricing & performance

Compare models All providers Data sources
Models served
28
of 1,109 tracked models
Mean output speed
45
tokens per second, averaged over
25 measured endpoints
Mean latency
2.1s
time to first token, averaged over
25 measured endpoints
Cheapest blended
$0.068
per 1M tokens at a 3:1
input:output blend
Output speed on Phala

Output tokens per second for the 25 of 28 models on Phala with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 28, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
88
83
80
71
68
68
67
59
55
54
51
50
The Known Good
28 models on Phala
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V3.2 DeepSeek $1.00 $1.00 $1.00 8 2.2s 164k
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.20 $0.40 $0.25 68 1.5s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.44 $1.32 $0.66 36 1.1s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.45 $4.36 $2.18 55 1.5s 1.05M
Google: Gemma 3 27B Google $0.15 $0.46 $0.23 51 0.8s 262k
Google: Gemma 4 31B Google $0.15 $0.46 $0.23 68 1.0s 262k
Meta: Muse Glimmer 30B Meta $0.30 $1.10 $0.50 71 1.2s 131k
MiniMax: MiniMax M2.5 MiniMax $0.20 $1.38 $0.49 — — 197k
MoonshotAI: Kimi K2.5 Moonshot AI $0.60 $3.00 $1.20 26 2.0s 262k
MoonshotAI: Kimi K2.6 Moonshot AI $1.09 $4.60 $1.97 37 1.4s 262k
MoonshotAI: Kimi K3 Moonshot AI $3.00 $15.00 $6.00 19 5.1s 1.05M
OpenAI: gpt-oss-120b OpenAI $0.15 $0.60 $0.26 67 1.2s 131k
OpenAI: gpt-oss-20b OpenAI $0.040 $0.15 $0.068 54 0.4s 131k
Qwen: Qwen2.5 7B Instruct Alibaba $0.10 $0.20 $0.12 59 0.3s 33k
Qwen: Qwen3 30B A3B Instruct 2507 Alibaba $0.15 $0.55 $0.25 88 3.1s 262k
Qwen: Qwen3 VL 30B A3B Instruct Alibaba $0.20 $0.70 $0.33 — — 128k
Qwen: Qwen3.5 397B A17B Alibaba $0.55 $3.50 $1.29 21 1.9s 262k
Qwen: Qwen3.5-27B Alibaba $0.30 $2.40 $0.82 12 1.0s 262k
Qwen: Qwen3.6 27B Alibaba $0.32 $2.70 $0.92 11 7.6s 262k
Qwen: Qwen3.6 35B A3B Alibaba $0.20 $1.27 $0.47 80 2.6s 262k
Qwen: Qwen3.8 27B Alibaba $0.30 $3.00 $0.97 23 2.3s 262k
Tencent: Hy3 Tencent $0.15 $0.64 $0.27 40 1.6s 262k
Z.ai: GLM 4.7 Z.ai $0.85 $3.30 $1.46 31 1.8s 131k
Z.ai: GLM 5 Z.ai $1.20 $3.50 $1.77 — — 203k
Z.ai: GLM 5.1 Z.ai $1.21 $4.20 $1.96 26 2.9s 203k
Z.ai: GLM 5.2 Z.ai $1.26 $3.00 $1.70 50 1.9s 1.05M
Z.ai: GLM 5.3 Z.ai $1.40 $4.40 $2.15 42 2.4s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.15 $0.50 $0.24 83 3.5s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Phala are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.