Phala — pricing & performance
Models served
19
of 908 tracked models
Mean output speed
42
tokens per second, averaged over
16 measured endpoints
16 measured endpoints
Mean latency
2.2s
time to first token, averaged over
16 measured endpoints
16 measured endpoints
Cheapest blended
$0.055
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Phala
Median output tokens per second for each model this host serves, derived from OpenRouter endpoint telemetry. Higher is better. We do not run these measurements ourselves.
12 of 19 models ▾
☰⚙⇩
+Add model from specific provider
The Known Good
19 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 | 10 | 3.9s | 164k |
Google: Gemma 3 27B
|
$0.15 | $0.46 | $0.23 | 15 | 1.7s | 262k | |
|
Google: Gemma 4 31B
|
$0.15 | $0.46 | $0.23 | 16 | 1.5s | 262k | |
MiniMax: MiniMax M2.5
|
MiniMax | $0.20 | $1.38 | $0.49 | 29 | 1.5s | 197k |
MoonshotAI: Kimi K2.5
|
Moonshot AI | $0.60 | $3.00 | $1.20 | 37 | 1.4s | 262k |
|
MoonshotAI: Kimi K2.6
|
Moonshot AI | $1.09 | $4.60 | $1.97 | — | — | 262k |
OpenAI: gpt-oss-120b
|
OpenAI | $0.15 | $0.60 | $0.26 | 82 | 0.8s | 131k |
|
OpenAI: gpt-oss-20b
|
OpenAI | $0.040 | $0.15 | $0.068 | 52 | 0.7s | 131k |
Qwen: Qwen2.5 7B Instruct
|
Alibaba | $0.040 | $0.10 | $0.055 | 35 | 0.5s | 33k |
|
Qwen: Qwen3 30B A3B Instruct 2507
|
Alibaba | $0.15 | $0.55 | $0.25 | 78 | 9.0s | 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 | 82 | 1.7s | 262k |
|
Qwen: Qwen3.5-27B
|
Alibaba | $0.30 | $2.40 | $0.82 | 51 | 1.4s | 262k |
|
Qwen: Qwen3.6 27B
|
Alibaba | $0.32 | $2.70 | $0.92 | 30 | 2.1s | 262k |
|
Qwen: Qwen3.6 35B A3B
|
Alibaba | $0.20 | $1.27 | $0.47 | 47 | 1.5s | 262k |
Z.ai: GLM 4.7
|
Z.ai | $0.85 | $3.30 | $1.46 | 31 | 3.6s | 131k |
|
Z.ai: GLM 5
|
Z.ai | $1.20 | $3.50 | $1.77 | 38 | 1.7s | 203k |
|
Z.ai: GLM 5.1
|
Z.ai | $1.21 | $4.20 | $1.96 | — | — | 203k |
|
Z.ai: GLM 5.2
|
Z.ai | $1.40 | $4.40 | $2.15 | 48 | 2.0s | 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.