Skip to content

Phala

Inference host · 18 models · 18 priced routes

Models on Phala

ModelIn / out per 1M
Qwen2.5 7B Instruct
Phala
$0.1 / $0.2Same vs headline
GLM 5.3 Flash
Phala, fp8, fp8
$0.128 / $0.425+194% vs headline
gpt-oss-120b
Phala
$0.15 / $0.6+304% vs headline
Qwen3.6 35B A3B
Phala
$0.2 / $1.27+120% vs headline
DeepSeek V4.1 Flash
Phala
$0.276 / $1.1+84% vs headline
Muse Glimmer 30B
Phala
$0.3 / $1.1Same vs headline
DeepSeek V4 Flash 0731
Phala
$0.44 / $1.32+733% vs headline
Qwen3.8 27B
Phala
$0.199 / $2.08-30% vs headline
Qwen3.5-27B
Phala
$0.3 / $2.4+54% vs headline
Qwen3.6 27B
Phala
$0.32 / $2.7-10% vs headline
DeepSeek V3.2
Phala
$1 / $1+327% vs headline
Qwen3.5 397B A17B
Phala
$0.55 / $3.5+47% vs headline
GLM 5.3
Phala
$0.84 / $2.64+50% vs headline
GLM 5.2
Phala, fp8, fp8
$1.26 / $3+97% vs headline
GLM 5.1
Phala
$1.21 / $4.2+32% vs headline
Kimi K2.6
Phala
$1.09 / $4.6+141% vs headline
DeepSeek V4 Pro 0813
Phala
$1.45 / $4.36+120% vs headline
Kimi K3
Phala
$2.1 / $10.5+27% vs headline

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.